© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91220
    Prev
    Next
    INDEX
    Explanations

    into

    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
     nastro
    -0.42
     Next
    -0.39
     ModelExpression
    -0.38
     thereupon
    -0.38
    .
    -0.38
     at
    -0.37
    ABULARY
    -0.37
    .'
    -0.37
    #[
    -0.36
     consequently
    -0.35
    POSITIVE LOGITS
     Roskov
    0.85
     nakalista
    0.78
    Архівовано
    0.75
    DockStyle
    0.73
    ftagPool
    0.72
    FormTagHelper
    0.69
    انيف
    0.69
    openConnection
    0.66
    intios
    0.65
    GEBURTSDATUM
    0.65
    Activations Density 0.000%

    No Known Activations