© 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. 74522
    Prev
    Next
    INDEX
    Explanations

    3

    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
    -0.78
     Roskov
    -0.69
    帖最后由
    -0.68
     Савезне
    -0.68
    ंदीखरीदारी
    -0.64
    Diweddarwch
    -0.60
    webElementXpaths
    -0.59
    Искәрмәләр
    -0.59
     estekak
    -0.56
    InjectAttribute
    -0.56
    POSITIVE LOGITS
     dzień
    0.45
     marrone
    0.43
     Mirza
    0.42
     outwards
    0.42
     involuc
    0.42
    Longueur
    0.40
    室內
    0.40
     calldata
    0.40
     dimensione
    0.40
    żo
    0.40
    Activations Density 0.005%

    No Known Activations