© 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. 41123
    Prev
    Next
    INDEX
    Explanations

    predictor

    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
     pleaſure
    -0.82
     raiſ
    -0.78
     itſelf
    -0.77
    extAlignment
    -0.70
     poffe
    -0.70
     myſelf
    -0.68
     themſelves
    -0.66
     Jefus
    -0.66
    RenderAtEndOf
    -0.66
     Houſe
    -0.65
    POSITIVE LOGITS
     of
    0.56
    رشف
    0.52
     Go
    0.51
     Ca
    0.51
    ERD
    0.51
     Gr
    0.49
    DebuggerStep
    0.49
     Gra
    0.48
    er
    0.48
     actor
    0.48
    Activations Density 0.101%

    No Known Activations