© 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. 44134
    Prev
    Next
    INDEX
    Explanations

    approach

    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
     approach
    -1.42
    approach
    -1.17
     Approach
    -1.14
    Approach
    -1.06
     APPROACH
    -0.93
     approaches
    -0.90
     approche
    -0.82
     Approaches
    -0.72
     pendekatan
    -0.66
     approached
    -0.65
    POSITIVE LOGITS
    ✨:
    0.66
    oredCriteria
    0.60
    HasAnnotation
    0.58
    سطس
    0.55
    complexContent
    0.54
     distanciation
    0.54
    Hochspringen
    0.53
     Paglinawan
    0.53
    клопе
    0.52
     المعيارى
    0.52
    Activations Density 0.742%

    No Known Activations