© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75059
    Prev
    Next
    INDEX
    Explanations

    Code and descriptions

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     Kategor
    -0.49
    posite
    -0.47
    ClientSize
    -0.47
    SerializedSize
    -0.46
    aure
    -0.46
    ous
    -0.46
     Kame
    -0.46
    ínio
    -0.45
    agory
    -0.44
     Spo
    -0.44
    POSITIVE LOGITS
     walks
    0.76
    parsedMessage
    0.66
     stripes
    0.65
    writeFieldEnd
    0.63
     Walks
    0.60
    walks
    0.59
    ⓘ
    0.59
     AspNetCore
    0.58
     spec
    0.56
    WebpackPlugin
    0.56
    Activations Density 0.000%

    No Known Activations