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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74422
    Prev
    Next
    INDEX
    Explanations

    Scientific/bureaucratic texts

    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
    twimg
    -0.69
    ❋
    -0.65
    PreferredItem
    -0.63
    expandindo
    -0.60
    providedIn
    -0.60
    UnitTesting
    -0.59
    plotlib
    -0.59
    WireFormatLite
    -0.58
    ValueStyle
    -0.58
    Personensuche
    -0.57
    POSITIVE LOGITS
     cat
    0.63
     ender
    0.55
     intermediary
    0.53
    cat
    0.46
    rawQuery
    0.45
     ana
    0.45
    herin
    0.45
    me
    0.45
     solute
    0.44
     metabolism
    0.43
    Activations Density 0.000%

    No Known Activations