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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13202
    Prev
    Next
    INDEX
    Explanations

    documents/reports

    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
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.57
    haustible
    -0.56
    Witam
    -0.54
    Rohy
    -0.53
    Indented
    -0.52
    verständlich
    -0.52
    ungalow
    -0.52
    wheels
    -0.51
    cheer
    -0.51
    plevel
    -0.50
    POSITIVE LOGITS
    Referències
    0.55
    ⓧ
    0.54
    avut
    0.52
    providedIn
    0.50
    \{\\
    0.49
    Atsauces
    0.47
     ModelExpression
    0.46
    Cyfeiriadau
    0.44
    UrlResolution
    0.43
    agulation
    0.42
    Activations Density 0.004%

    No Known Activations