© 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. 5-CLT-HP
    7. 6316
    Prev
    Next
    INDEX
    Explanations

    end of snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.90
     nærm
    -0.47
     įsi
    -0.47
     føl
    -0.46
     tæt
    -0.46
     habet
    -0.46
     liitty
    -0.45
     nær
    -0.45
     eorum
    -0.45
     fuis
    -0.43
    POSITIVE LOGITS
    EndInit
    0.66
    HomeAsUpEnabled
    0.64
    XmlType
    0.63
     combineReducers
    0.62
    AutoScaleMode
    0.60
    Hochspringen
    0.60
     Vapour
    0.60
    WebMethod
    0.57
    Välislingid
    0.57
     يتيمه
    0.56
    Activations Density 0.000%

    No Known Activations