© 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. 44049
    Prev
    Next
    INDEX
    Explanations

    "of"

    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
     SwitchCompat
    -0.59
    Попис
    -0.59
    
    -0.56
    UserScript
    -0.54
    chtenstein
    -0.53
    riche
    -0.52
    umet
    -0.52
    suya
    -0.52
    讐
    -0.52
    zeigt
    -0.52
    POSITIVE LOGITS
    Bronnen
    0.57
    "]="
    0.50
    kloped
    0.50
    IsContent
    0.50
    Revenir
    0.49
     lawmakers
    0.49
     NIM
    0.49
    '])->
    0.48
    ChildScrollView
    0.47
    ValueStyle
    0.47
    Activations Density 0.131%

    No Known Activations