© 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. 74710
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, science

    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
    Diwedd
    -0.78
     anhydride
    -0.66
     Duma
    -0.63
     userService
    -0.62
     ActionResult
    -0.60
    참고
    -0.60
    hdys
    -0.59
     Signalez
    -0.59
     Paddington
    -0.59
    aira
    -0.57
    POSITIVE LOGITS
     mergeFrom
    0.57
    GraphicsUnit
    0.50
     National
    0.40
    BeginInit
    0.40
    AnchorStyles
    0.38
     NP
    0.38
     Na
    0.37
    
    0.35
    +#+#
    0.34
     kiệm
    0.34
    Activations Density 0.000%

    No Known Activations