© 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. 5-CLT-HP
    7. 92571
    Prev
    Next
    INDEX
    Explanations

    news headlines

    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
     betweenstory
    -0.58
    jsxFileName
    -0.56
    Биография
    -0.53
    GenerationType
    -0.53
    ificato
    -0.51
    StoreMessageInfo
    -0.51
     bienvenue
    -0.50
    Initializable
    -0.49
    maxAge
    -0.48
     Single
    -0.48
    POSITIVE LOGITS
    .
    0.77
     تضيفلها
    0.62
    felde
    0.52
    JsonPropertyName
    0.51
    PYX
    0.50
     pessoais
    0.49
    bkz
    0.48
     vooraf
    0.47
     contemporaneous
    0.47
    camion
    0.46
    Activations Density 0.000%

    No Known Activations