© 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. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3598
    Prev
    Next
    INDEX
    Explanations

    occurrences of error messages

    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
     mapStateToProps
    -0.87
    NUMX
    -0.79
    NUC
    -0.77
    Xna
    -0.73
    BibitemShut
    -0.71
     vf
    -0.70
     Yorke
    -0.70
    bibfield
    -0.70
    enance
    -0.69
     Montoya
    -0.69
    POSITIVE LOGITS
    err
    1.28
     err
    0.96
    ERR
    0.75
     Serr
    0.74
     Terr
    0.71
     Cerr
    0.67
    ser
    0.66
    optString
    0.65
     Perr
    0.65
    t
    0.65
    Activations Density 0.058%

    No Known Activations