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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42926
    Prev
    Next
    INDEX
    Explanations

    descriptive language

    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
     substantial
    -0.91
     huge
    -0.78
    huge
    -0.75
     Substantial
    -0.75
     generous
    -0.72
     Huge
    -0.72
    substantial
    -0.71
     considerable
    -0.71
     HUGE
    -0.68
     large
    -0.65
    POSITIVE LOGITS
    
    0.91
    ^(@)
    0.79
    RenderAtEndOf
    0.78
    ⓧ
    0.75
     виправивши
    0.75
    ControllerAdvice
    0.73
     itſelf
    0.72
    Personendaten
    0.71
    хьтан
    0.69
    WriteAttribute
    0.69
    Activations Density 0.084%

    No Known Activations