© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    reviews/advertisements

    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
    -
    -0.61
     the
    -0.49
     an
    -0.47
     How
    -0.46
    fall
    -0.44
    falls
    -0.44
    Độ
    -0.43
    education
    -0.42
    standing
    -0.42
    an
    -0.42
    POSITIVE LOGITS
     MessageBoxIcon
    0.83
    ViewImports
    0.72
     NSCoder
    0.70
     Púb
    0.69
    forName
    0.68
    HtmlAttribute
    0.68
    ExtendWith
    0.68
    httphttps
    0.67
    TemporalType
    0.66
    CodeAttribute
    0.66
    Activations Density 0.194%

    No Known Activations