© 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. 41613
    Prev
    Next
    INDEX
    Explanations

    approach or aspect

    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
     itſelf
    -0.85
     Theſe
    -0.80
     Efq
    -0.79
     Majefty
    -0.75
    ſelf
    -0.74
     ſtate
    -0.73
     myſelf
    -0.72
     purpoſe
    -0.69
     auffi
    -0.68
     Jefus
    -0.68
    POSITIVE LOGITS
     of
    0.66
     for
    0.61
     to
    0.50
     featuring
    0.49
     on
    0.48
     allowing
    0.46
     more
    0.45
     providing
    0.43
     comprising
    0.43
     figures
    0.42
    Activations Density 0.015%

    No Known Activations