© 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. 1-CLT-HP
    7. 14353
    Prev
    Next
    INDEX
    Explanations

    repair

    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
    Heinz
    -0.57
     Heinz
    -0.55
     aé
    -0.45
     pulito
    -0.44
     reino
    -0.43
     كنت
    -0.41
     reliance
    -0.40
    كل
    -0.40
     aggiun
    -0.40
     Tuch
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.95
    rungsseite
    0.74
     surla
    0.73
     تضيفلها
    0.72
     utafitiHapana
    0.69
     disambiguazione
    0.68
     @"/
    0.68
    Datuak
    0.66
    }{*}{}
    0.66
    PreferredItem
    0.65
    Activations Density 0.044%

    No Known Activations