© 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. 28300
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases expressing emotion

    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
     Abp
    -0.98
    buttonBar
    -0.82
    Rüyada
    -0.71
    jws
    -0.67
    ectoria
    -0.65
     Jord
    -0.63
    PreferredItem
    -0.63
    Dort
    -0.60
    kháu
    -0.60
    Hochspringen
    -0.58
    POSITIVE LOGITS
    Literals
    0.63
    Parcelize
    0.63
    batterie
    0.60
    cloudfront
    0.59
    filet
    0.57
     ویکی‌پدیا
    0.57
     Antropo
    0.56
    tagHelperRunner
    0.55
    눠
    0.55
    زارش
    0.55
    Activations Density 0.015%

    No Known Activations