© 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. 9688
    Prev
    Next
    INDEX
    Explanations

    instances of relational symbols typically used in programming or mathematical 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
    Aktualisiert
    -0.68
     lenker
    -0.66
    তথ্যসূত্র
    -0.66
    EndContext
    -0.63
    WithEmail
    -0.60
     izan
    -0.60
     CiNii
    -0.58
     disambiguazione
    -0.57
    RenderAtEndOf
    -0.56
    出版年
    -0.56
    POSITIVE LOGITS
    offsetof
    0.62
    исленность
    0.55
    erein
    0.55
    entu
    0.54
    __":
    0.51
     Jn
    0.51
    __(/*!
    0.51
     Sauer
    0.50
    linspace
    0.50
    vér
    0.49
    Activations Density 0.280%

    No Known Activations