© 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. 45750
    Prev
    Next
    INDEX
    Explanations

    0

    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
    igheid
    -0.48
    kwds
    -0.44
    unit
    -0.41
     IndexPath
    -0.40
    HtmlAttribute
    -0.40
     PopupWindow
    -0.40
    GoogleApiClient
    -0.38
     чём
    -0.37
     Hierro
    -0.37
     lost
    -0.36
    POSITIVE LOGITS
     transfieras
    0.76
     ModelExpression
    0.71
    Revenir
    0.71
     كومونز
    0.67
    expandindo
    0.65
    Viited
    0.65
    ærke
    0.64
     ostavi
    0.63
    0
    0.63
     חיצוניים
    0.62
    Activations Density 0.064%

    No Known Activations