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. 73870
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     surla
    -0.78
    ConstraintMaker
    -0.71
    Geplaatst
    -0.66
    IsMutable
    -0.64
    BuilderFactory
    -0.63
     onlyOwner
    -0.58
    WebMethod
    -0.58
    OGND
    -0.58
    extAlignment
    -0.55
    ollectionView
    -0.54
    POSITIVE LOGITS
    gadas
    0.49
    huri
    0.49
    prising
    0.49
    tising
    0.48
    inerja
    0.48
    EOUS
    0.48
    horabuena
    0.46
    hiri
    0.45
    ёз
    0.45
    íslu
    0.44
    Activations Density 0.002%

    No Known Activations