© 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. 91646
    Prev
    Next
    INDEX
    Explanations

    switch

    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
    DockStyle
    -0.75
    /***/
    -0.59
    esModule
    -0.54
    AxisAlignment
    -0.52
    atorship
    -0.49
    sistors
    -0.48
     Change
    -0.48
     Changes
    -0.46
     '@/
    -0.46
    sistor
    -0.46
    POSITIVE LOGITS
    Koordin
    0.64
     purpoſe
    0.62
    setVerticalGroup
    0.60
     ſche
    0.56
     thérape
    0.54
     ſy
    0.54
     traseiro
    0.54
    actéristique
    0.53
     PagesJaunes
    0.52
     hvě
    0.52
    Activations Density 0.003%

    No Known Activations