Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12752
    Prev
    Next
    INDEX
    Explanations

    compression

    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
     Heron
    -0.56
    Personendaten
    -0.53
    tabil
    -0.50
    Ryu
    -0.47
    ensitive
    -0.47
     estren
    -0.46
    сшта
    -0.46
     Magn
    -0.45
     pe
    -0.44
    eper
    -0.44
    POSITIVE LOGITS
     referenties
    0.69
    IntoConstraints
    0.67
    fitrión
    0.60
     onPostExecute
    0.56
     Réponses
    0.54
    DoubleQuotes
    0.54
    êmio
    0.53
     MenuView
    0.53
     onBind
    0.53
    HandlerContext
    0.52
    Activations Density 0.019%

    No Known Activations