© 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. 97755
    Prev
    Next
    INDEX
    Explanations

    Beginning of documents

    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
    
    -0.85
     للمعارف
    -0.84
     nakalista
    -0.82
    rungsseite
    -0.78
    EDEFAULT
    -0.77
     متعلقه
    -0.75
    WebVitals
    -0.75
    elemField
    -0.74
     autorytatywna
    -0.74
    findpost
    -0.73
    POSITIVE LOGITS
     mental
    0.47
     extra
    0.43
     
    0.43
    salut
    0.42
    riger
    0.41
    νω
    0.41
    thalene
    0.41
     Mati
    0.40
    houding
    0.40
    اتر
    0.40
    Activations Density 0.094%

    No Known Activations