© 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. 5-CLT-HP
    7. 95164
    Prev
    Next
    INDEX
    Explanations

    of

    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
     disambiguazione
    -0.60
    GraphicsUnit
    -0.58
    Еще
    -0.55
    готавли
    -0.51
    AlterField
    -0.50
     retrou
    -0.50
    FXMLLoader
    -0.50
     endwhile
    -0.50
    曖昧さ回避
    -0.50
     uniting
    -0.50
    POSITIVE LOGITS
     type
    0.63
     types
    0.60
    PyExc
    0.60
     phases
    0.60
     Type
    0.57
    knapp
    0.53
    RefNanny
    0.52
     Perspective
    0.52
    RTEE
    0.52
     method
    0.51
    Activations Density 0.002%

    No Known Activations