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

    Neuronpedia

    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. 3921
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions related to pregnancy and reproduction

    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
    1150
    +0.14
    0.4%
    2034
    +0.11
    0.3%
    1967
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.14
    0.07
    1438
    +0.11
    0.05
    1013
    +0.11
    0.07
    Negative Logits
    Fordítás
    -0.73
    Nguy
    -0.67
     Compañ
    -0.67
    Glej
    -0.65
    Vaata
    -0.64
     persua
    -0.64
    ἐ
    -0.64
    Sklici
    -0.63
     servem
    -0.63
    ">...
    -0.63
    POSITIVE LOGITS
    .
    0.62
     Warlock
    0.52
     idr
    0.51
     herre
    0.51
     NSCoder
    0.51
     merve
    0.50
    namely
    0.50
     oreilles
    0.49
     étages
    0.49
     abf
    0.49
    Activations Density 0.558%

    No Known Activations