© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9674
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions within programming or code snippets

    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
     noires
    -0.51
    endpush
    -0.50
     servici
    -0.49
    astify
    -0.48
     complètes
    -0.47
     blanches
    -0.47
    pejo
    -0.46
     Sénat
    -0.45
     paradiso
    -0.45
    lgari
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.84
    tagHelperRunner
    0.67
     kaarangay
    0.66
    OGND
    0.63
    astéroïdes
    0.61
    Autoritní
    0.60
    abestanden
    0.59
    ResumeLayout
    0.57
    Glej
    0.57
     الرياضيه
    0.55
    Activations Density 0.010%

    No Known Activations