© 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. 4330
    Prev
    Next
    INDEX
    Explanations

    of

    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
     automatiques
    -0.56
     profondità
    -0.54
     loisirs
    -0.53
     termurah
    -0.50
     étoient
    -0.50
     extérieures
    -0.50
    Flammability
    -0.49
     présentée
    -0.49
    if
    -0.49
     avoient
    -0.48
    POSITIVE LOGITS
     this
    1.03
    complexContent
    0.67
    matchCondition
    0.61
     This
    0.61
     этого
    0.57
     لهذا
    0.57
     هذا
    0.56
     للاسماء
    0.56
     course
    0.54
    nadequate
    0.54
    Activations Density 0.007%

    No Known Activations