© 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. 42516
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    Personendaten
    -1.02
     Efq
    -0.80
     Jefus
    -0.76
    KURZBESCHREIBUNG
    -0.73
     itſelf
    -0.73
     pinulongan
    -0.72
    adays
    -0.71
     ―――――
    -0.69
     ModelExpression
    -0.69
     Houſe
    -0.68
    POSITIVE LOGITS
    elemField
    0.52
    printStackTrace
    0.46
     الخام
    0.45
     volt
    0.44
    ante
    0.44
     Bar
    0.43
     Mann
    0.42
    tista
    0.42
     Planners
    0.41
     Man
    0.41
    Activations Density 2.046%

    No Known Activations