© 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. 1942
    Prev
    Next
    INDEX
    Explanations

    HTML links

    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
    帖最后由
    -0.67
    MigrationBuilder
    -0.57
    uldron
    -0.56
     VIDEOTAPE
    -0.55
    UnknownFieldSet
    -0.55
    rachtet
    -0.54
     Reverso
    -0.53
     MOQ
    -0.53
    utenant
    -0.52
    XmlType
    -0.52
    POSITIVE LOGITS
     link
    1.77
     href
    1.61
     Link
    1.59
    link
    1.58
    Link
    1.54
     links
    1.52
    href
    1.49
     URL
    1.45
     LINK
    1.41
     hyperlink
    1.41
    Activations Density 1.051%

    No Known Activations