© 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. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4266
    Prev
    Next
    INDEX
    Explanations

    function definitions or calls in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"";
    -0.83
     '/';
    -0.82
     "";
    -0.79
    qrstuvwxyz
    -0.76
     "");
    -0.75
    [];
    -0.74
    MessageOf
    -0.71
     '-';
    -0.71
     '';
    -0.68
     ")");
    -0.68
    POSITIVE LOGITS
    enumi
    0.62
    chata
    0.54
    WithMany
    0.53
    InSection
    0.53
     Iss
    0.49
    kään
    0.49
     cref
    0.49
    NavController
    0.48
    ExecutionContext
    0.47
    bukkit
    0.46
    Activations Density 0.002%

    No Known Activations