© 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. 1-CLT-HP
    7. 14875
    Prev
    Next
    INDEX
    Explanations

    you

    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
     are
    -0.86
    '
    -0.79
    ’
    -0.73
     can
    -0.65
     have
    -0.64
     had
    -0.63
     were
    -0.61
     begin
    -0.61
     get
    -0.60
     will
    -0.59
    POSITIVE LOGITS
     itſelf
    1.05
     Monfieur
    0.97
     Jefus
    0.95
     Efq
    0.95
     poffible
    0.93
     Theſe
    0.93
     pleaſure
    0.91
     Reſ
    0.91
     occaf
    0.90
     Conſ
    0.89
    Activations Density 0.034%

    No Known Activations