© 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. 820
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and comparisons in expressions

    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
    AutoScaleMode
    -0.93
    Collegamenti
    -0.62
     >=",
    -0.59
     Préférences
    -0.59
     makeStyles
    -0.57
     analyse
    -0.56
    AccessorTable
    -0.55
     Bauhaus
    -0.54
    loroethene
    -0.54
    DeleteBehavior
    -0.54
    POSITIVE LOGITS
     الحره
    0.69
    ConstraintMaker
    0.67
    ⎩
    0.57
     giác
    0.56
    enumii
    0.56
    cock
    0.56
    classNames
    0.53
    richtungen
    0.52
    )");
    0.52
    ients
    0.51
    Activations Density 0.138%

    No Known Activations