© 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. 985
    Prev
    Next
    INDEX
    Explanations

    caricature

    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
    IA
    -0.66
     /\.
    -0.56
     sumpay
    -0.56
     flé
    -0.56
    ature
    -0.55
    })()
    -0.55
    xffffffff
    -0.54
    drawSprites
    -0.53
     EconPapers
    -0.53
    お楽しみに
    -0.53
    POSITIVE LOGITS
    BeginInit
    0.60
    ůr
    0.46
    DeleteBehavior
    0.46
    γε
    0.44
    NavigationView
    0.44
    Бахар
    0.43
    czywiście
    0.43
    penn
    0.43
    Κ
    0.42
     vigil
    0.42
    Activations Density 0.020%

    No Known Activations