© 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. 0-CLT-HP
    7. 94649
    Prev
    Next
    INDEX
    Explanations

    stopping actions

    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
     to
    -0.67
    t
    -0.65
    v
    -0.62
    e
    -0.61
    to
    -0.59
    g
    -0.59
    stop
    -0.57
    ded
    -0.56
    d
    -0.56
    -
    -0.56
    POSITIVE LOGITS
     myſelf
    1.14
    TestingModule
    1.05
    parsedMessage
    1.05
     raiſ
    0.98
     itſelf
    0.98
     Efq
    0.97
    UnitTesting
    0.94
     uſed
    0.94
     Jefus
    0.93
     Majefty
    0.92
    Activations Density 0.041%

    No Known Activations