© 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. 0-CLT-HP
    7. 1046
    Prev
    Next
    INDEX
    Explanations

    Welcome

    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
     CreateTagHelper
    -0.68
     quæ
    -0.66
     RISERV
    -0.66
     الرياضيه
    -0.60
     defaultstate
    -0.60
     MainAxisSize
    -0.59
     NACIONAL
    -0.59
    Personendaten
    -0.59
    Obrázky
    -0.58
     كومونز
    -0.58
    POSITIVE LOGITS
    ↵↵
    0.60
    ↵
    0.58
    ly
    0.56
    /');
    0.54
     To
    0.53
    ец
    0.52
     One
    0.51
     Matter
    0.51
     Desk
    0.50
     The
    0.50
    Activations Density 0.042%

    No Known Activations