© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4537
    Prev
    Next
    INDEX
    Explanations

    before

    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
     frattempo
    -0.59
     occaf
    -0.57
    Placed
    -0.57
     Achieving
    -0.57
     Expansion
    -0.57
     Gives
    -0.57
     Cleaner
    -0.57
     Hosting
    -0.56
     Placed
    -0.56
     Educate
    -0.56
    POSITIVE LOGITS
    #+#
    0.68
     بيها
    0.58
    GoogleApiClient
    0.57
    存于互联网档案馆
    0.55
    AsUp
    0.45
    Obrázky
    0.45
    UnsafeEnabled
    0.45
    SVN
    0.44
    ніципалі
    0.44
    ￡
    0.44
    Activations Density 0.001%

    No Known Activations