© 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. 22-RES-MATRYOSHKA-DC
    7. 1582
    Prev
    Next
    INDEX
    Explanations

    words that start with "Com", especially if followed by "m"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    GEBURTSDATUM
    -0.82
     ExecuteAsync
    -0.81
    \{\\
    -0.80
    StoreMessageInfo
    -0.77
    脚注の使い方
    -0.76
    EndGlobalSection
    -0.76
     ModelExpression
    -0.74
    AndEndTag
    -0.74
     tartalomajánló
    -0.73
    enterOuterAlt
    -0.73
    POSITIVE LOGITS
    Com
    0.58
     Com
    0.54
    NamedQueries
    0.52
     COM
    0.52
    COM
    0.52
     favourably
    0.50
     disponibilités
    0.50
    ğini
    0.48
     Unab
    0.47
     CHAM
    0.47
    Activations Density 0.533%

    No Known Activations