© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95005
    Prev
    Next
    INDEX
    Explanations

    intelligence

    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
    expandindo
    -0.86
    riguez
    -0.54
    belo
    -0.46
    tabile
    -0.45
    ist
    -0.44
     Weise
    -0.43
    脚注の使い方
    -0.43
    ب
    -0.43
    mall
    -0.42
     Cub
    -0.42
    POSITIVE LOGITS
     agencies
    0.83
     community
    0.72
     communities
    0.70
     officers
    0.69
     agences
    0.69
     officials
    0.65
    COMMUNITY
    0.65
     agence
    0.64
     COMMUNITY
    0.64
    community
    0.64
    Activations Density 0.001%

    No Known Activations