© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5595
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
    RectangleBorder
    -0.71
    usercontent
    -0.55
    ordo
    -0.50
     صوتيه
    -0.50
    DockStyle
    -0.50
     Horses
    -0.49
     resourceCulture
    -0.49
    lato
    -0.48
     Wikispecies
    -0.48
     createStore
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.63
    czegó
    0.56
     disambiguazione
    0.55
    addGap
    0.53
    AsUp
    0.52
    ⓧ
    0.50
    moveToFirst
    0.48
     ممكن
    0.46
    Precision
    0.46
     تضيفلها
    0.46
    Activations Density 0.007%

    No Known Activations