© 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. 10322
    Prev
    Next
    INDEX
    Explanations

    course

    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
    gestone
    -0.53
    ⓧ
    -0.50
    SourceChecksum
    -0.48
    MLLoader
    -0.46
     course
    -0.45
    GenerationType
    -0.44
    TestingModule
    -0.43
    complexContent
    -0.39
    ituary
    -0.39
     of
    -0.39
    POSITIVE LOGITS
     myſelf
    0.77
     nakalista
    0.73
     mapStateToProps
    0.70
    ſelf
    0.70
     ainfi
    0.69
     ſeveral
    0.69
     ſtate
    0.68
     mijne
    0.67
     itſelf
    0.66
     zijne
    0.66
    Activations Density 0.048%

    No Known Activations