Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31281
    Prev
    Next
    INDEX
    Explanations

    unclear, but it seems to activate on random strings of letters and numbers

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.62
     &___
    -0.62
    //
    -0.62
    帖最后由
    -0.61
     ModelExpression
    -0.61
     كومونز
    -0.59
    лтемелер
    -0.59
     DialogInterface
    -0.59
     NgModule
    -0.56
     TestBed
    -0.56
    POSITIVE LOGITS
    parsedMessage
    0.81
    UnusedPrivate
    0.76
    ViewFeatures
    0.72
    vician
    0.66
    LookAnd
    0.65
    ьаж
    0.63
     Yani
    0.63
     Gregorian
    0.63
    SourceChecksum
    0.62
     itſelf
    0.61
    Activations Density 0.002%

    No Known Activations