© 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. 473
    Prev
    Next
    INDEX
    Explanations

    numbered events

    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
     HasFactory
    -0.71
    __":
    -0.67
     invokingState
    -0.64
     الرياضيه
    -0.62
    +");
    -0.62
    \{\\
    -0.56
    thâu
    -0.56
    المراجع
    -0.56
     ExecuteAsync
    -0.55
    MessageTagHelper
    -0.54
    POSITIVE LOGITS
     comunale
    0.57
     Pizarro
    0.54
     élas
    0.52
     orec
    0.50
     conquered
    0.50
     Brecht
    0.50
    RetentionPolicy
    0.50
     azi
    0.50
     invas
    0.49
    FRC
    0.49
    Activations Density 0.005%

    No Known Activations