© 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. 22663
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions related to statistics or probability theory

    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
    parsedMessage
    -0.76
    enschappelijke
    -0.66
    Hauptartikel
    -0.59
    ुनिया
    -0.57
    werkt
    -0.54
    .}}
    -0.53
     cucharada
    -0.52
    bewerken
    -0.51
    URLException
    -0.51
    CopyWith
    -0.51
    POSITIVE LOGITS
     BoxDecoration
    0.63
     nakalista
    0.59
    apimachinery
    0.57
    inWeight
    0.56
     uVar
    0.52
    resizingMask
    0.52
     saites
    0.52
    IFIED
    0.52
    oforte
    0.52
    RenderAtEndOf
    0.51
    Activations Density 0.014%

    No Known Activations