© 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. 5-CLT-HP
    7. 4729
    Prev
    Next
    INDEX
    Explanations

    prototype

    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
     fjor
    -0.52
     của
    -0.50
    lägg
    -0.47
    SourceChecksum
    -0.43
     årene
    -0.43
     étrangers
    -0.43
     moindre
    -0.42
     Bedien
    -0.42
     autorytatywna
    -0.41
     åren
    -0.41
    POSITIVE LOGITS
    ⓧ
    0.79
    IntoConstraints
    0.65
     IDEA
    0.63
     Arian
    0.63
     gddr
    0.62
     Theſe
    0.62
     DbContext
    0.60
     dreamstime
    0.60
     Etsy
    0.59
     Vri
    0.59
    Activations Density 0.002%

    No Known Activations