© 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. 20-CLT-HP
    7. 74526
    Prev
    Next
    INDEX
    Explanations

    exactness

    np_max-act-logits · 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
    SourceChecksum
    -0.83
     pinulongan
    -0.78
     kasarigan
    -0.73
     defaultstate
    -0.70
    elemField
    -0.67
     ويكيپيديا
    -0.67
    ⓧ
    -0.66
    GEBURTSDATUM
    -0.62
    AndEndTag
    -0.59
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
     clearly
    0.66
     specifically
    0.63
     precisely
    0.59
     objectively
    0.59
     Clearly
    0.58
     simply
    0.55
     fully
    0.55
     Specifically
    0.54
     plainly
    0.54
     SPECIFIC
    0.52
    Activations Density 0.004%

    No Known Activations