© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6136
    Prev
    Next
    INDEX
    Explanations

    names or references related to a specific person named 'Muhammad' or 'Muhammad' in the context of news or articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1984
    +0.16
    0.7%
    411
    +0.14
    0.6%
    1127
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.16
    0.03
    411
    +0.14
    0.03
    662
    +0.13
    0.03
    Negative Logits
     كومونز
    -0.52
    HasColumnName
    -0.46
     Tages
    -0.45
     yarar
    -0.44
     زر
    -0.43
     człowiek
    -0.43
    FieldDescriptor
    -0.41
     키
    -0.41
    setDo
    -0.41
    htbp
    -0.40
    POSITIVE LOGITS
     Mu
    1.13
     exé
    1.10
    Mu
    1.08
     mu
    1.05
     simplif
    1.02
     MU
    0.95
     obé
    0.94
     MUT
    0.94
     sappi
    0.91
     munich
    0.91
    Activations Density 0.115%

    No Known Activations