© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42153
    Prev
    Next
    INDEX
    Explanations

    german

    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
     game
    -1.16
     GAME
    -1.10
    game
    -1.05
     Game
    -1.03
    GAME
    -0.96
    Game
    -0.90
    Personendaten
    -0.79
     Germany
    -0.79
     german
    -0.77
     German
    -0.75
    POSITIVE LOGITS
    <bos>
    0.69
    N
    0.63
    ي
    0.59
    K
    0.58
    z
    0.57
    脱
    0.57
    cy
    0.56
    k
    0.56
    G
    0.54
    '
    0.54
    Activations Density 0.100%

    No Known Activations