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. 0-CLT-HP
    4. 39303
    Prev
    Next
    INDEX
    Explanations

    peacefully

    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
     saucer
    -1.28
     насељу
    -0.84
     виправивши
    -0.84
    CloseOperation
    -0.78
    tagHelperRunner
    -0.76
    Vidite
    -0.76
    AnimationsModule
    -0.74
     linkovi
    -0.71
     CURIAM
    -0.69
    cplusplus
    -0.69
    POSITIVE LOGITS
    adv
    0.49
    Of
    0.47
    If
    0.46
    まま
    0.46
    Old
    0.45
    The
    0.44
    度は
    0.43
     dauern
    0.43
     mind
    0.43
    1
    0.42
    Activations Density 1.660%

    No Known Activations