© 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. 20-CLT-HP
    7. 75860
    Prev
    Next
    INDEX
    Explanations

    How

    np_max-act-logits · 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
    Naissance
    -0.69
     contextLoads
    -0.65
    +:+
    -0.59
     barriers
    -0.56
    RetentionPolicy
    -0.56
     mosso
    -0.56
    RenderAtEndOf
    -0.55
     NPS
    -0.53
     dikes
    -0.53
     Municipalidad
    -0.52
    POSITIVE LOGITS
    AxisAlignment
    0.69
    CloseOperation
    0.68
     autorytatywna
    0.57
    ScopeManager
    0.52
     stink
    0.51
     pretty
    0.50
    ArgsConstructor
    0.50
    inthe
    0.49
     mean
    0.48
     Pretty
    0.48
    Activations Density 0.002%

    No Known Activations