© 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. 91958
    Prev
    Next
    INDEX
    Explanations

    rate

    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
    ness
    -0.60
    rate
    -0.55
     ***!
    -0.53
     rate
    -0.52
    ly
    -0.52
    
    -0.52
    __*/
    -0.49
    nextProps
    -0.48
     the
    -0.47
     you
    -0.47
    POSITIVE LOGITS
    execSQL
    0.66
     moduli
    0.65
    hassee
    0.64
     doses
    0.61
     chopsticks
    0.61
     equations
    0.60
     medusa
    0.60
     SRA
    0.60
    aksanaan
    0.60
     orientations
    0.59
    Activations Density 0.403%

    No Known Activations