© 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. 0-CLT-HP
    4. 1057
    Prev
    Next
    INDEX
    Explanations

    can

    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
    клопе
    -0.70
     itſelf
    -0.70
     ſhe
    -0.69
     astronomers
    -0.68
     acquittal
    -0.65
    دانشنامهٔ
    -0.64
    yntaxException
    -0.62
    évaluateur
    -0.62
     clemen
    -0.62
     thyself
    -0.61
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    photobucket
    0.58
     EnglishChoose
    0.47
    
    0.47
    Personensuche
    0.46
     pop
    0.45
     multi
    0.45
    ANNES
    0.42
    дь
    0.41
    MultipartFile
    0.41
    Activations Density 0.220%

    No Known Activations