© 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. 44117
    Prev
    Next
    INDEX
    Explanations

    riction

    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
    setVerticalGroup
    -0.85
     ujednoznacz
    -0.75
     CURIAM
    -0.73
     defaultstate
    -0.65
    Życiorys
    -0.61
    sior
    -0.60
    culosis
    -0.59
    shire
    -0.57
    ThroughAttribute
    -0.57
     aDecoder
    -0.57
    POSITIVE LOGITS
    Hochspringen
    0.59
     financeira
    0.56
    aguya
    0.47
    HasAnnotation
    0.47
    idän
    0.45
     phenotype
    0.44
     ſtre
    0.44
     lead
    0.43
    vány
    0.43
    sodik
    0.43
    Activations Density 0.084%

    No Known Activations