© 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 EvalsExportsinterp-engineNEWAPI 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. 4688
    Prev
    Next
    INDEX
    Explanations

    mentions of Poland and related events or entities

    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
    1325
    +0.14
    0.4%
    1520
    +0.14
    0.4%
    370
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1520
    +0.14
    0.03
    370
    +0.14
    0.03
    1325
    +0.12
    0.02
    Negative Logits
     Krzysz
    -1.15
     Krzyż
    -0.95
    Witaj
    -0.90
     Komis
    -0.87
     Ży
    -0.82
     Szw
    -0.81
    : 
    -0.80
    cyj
    -0.80
    zyj
    -0.79
    Gdy
    -0.77
    POSITIVE LOGITS
     increa
    2.10
     depic
    2.05
     encomp
    2.04
     milf
    1.93
     impra
    1.92
     maneu
    1.92
     reluct
    1.92
     snoopy
    1.90
     inev
    1.90
     wherea
    1.89
    Activations Density 0.146%

    No Known Activations