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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73844
    Prev
    Next
    INDEX
    Explanations

    political

    np_max-act-logits · 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
     autorytatywna
    -0.55
    point
    -0.54
    faces
    -0.53
    Paran
    -0.52
    alha
    -0.51
    Naissance
    -0.51
     partea
    -0.51
    ENTIAL
    -0.51
     Wicidata
    -0.50
    แนว
    -0.50
    POSITIVE LOGITS
     AttributeSet
    0.55
    πως
    0.49
    poons
    0.48
    routeProvider
    0.47
     onPostExecute
    0.47
    istoitu
    0.47
    ranton
    0.46
    Hauptartikel
    0.45
    afel
    0.43
    InteropServices
    0.43
    Activations Density 0.002%

    No Known Activations