© 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. 94601
    Prev
    Next
    INDEX
    Explanations

    Computing/electronics abbreviations

    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
    RetentionPolicy
    -0.74
     Wikimedijinoj
    -0.71
     auffi
    -0.68
    PCs
    -0.67
     Monfieur
    -0.66
    APIs
    -0.65
    脚注の使い方
    -0.65
    RenderAtEndOf
    -0.65
     PCs
    -0.63
    zegovina
    -0.62
    POSITIVE LOGITS
     للمعارف
    0.57
    words
    0.43
     تانيه
    0.39
     ratified
    0.39
    rungsseite
    0.36
     that
    0.36
    offsetWidth
    0.36
     Rückkehr
    0.35
    </td>
    0.35
     drawn
    0.35
    Activations Density 0.064%

    No Known Activations