© 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. 1-CLT-HP
    7. 12325
    Prev
    Next
    INDEX
    Explanations

    uk

    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
    uk
    -1.52
    ukas
    -1.19
    UK
    -1.15
    ukan
    -1.01
     uk
    -0.99
    uka
    -0.97
     UK
    -0.94
    uki
    -0.92
    uker
    -0.91
    ukk
    -0.86
    POSITIVE LOGITS
    ิลปะ
    0.49
    Startup
    0.45
     carburetor
    0.44
    nocześnie
    0.43
    abestanden
    0.43
     armées
    0.43
     parlor
    0.42
    OV
    0.42
     Startup
    0.42
    sf
    0.42
    Activations Density 0.016%

    No Known Activations