© 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. 4-CLT-HP
    7. 871
    Prev
    Next
    INDEX
    Explanations

    it

    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
    styleable
    -0.44
    Ārējās
    -0.40
    icate
    -0.40
     дело
    -0.38
    istre
    -0.38
    raisemb
    -0.38
     nonatomic
    -0.37
    املة
    -0.37
     Comercio
    -0.37
    yn
    -0.37
    POSITIVE LOGITS
     any
    0.90
    GEBURTSDATUM
    0.85
    
    0.77
     >=",
    0.75
    tagHelperRunner
    0.75
    mybatisplus
    0.74
    RectangleBorder
    0.74
     дописавши
    0.73
    any
    0.72
    ArgsConstructor
    0.72
    Activations Density 0.003%

    No Known Activations