© 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. 39002
    Prev
    Next
    INDEX
    Explanations

    Weight

    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
     Anſ
    -1.02
     Monfieur
    -0.99
     obese
    -0.92
    poverty
    -0.92
     Efq
    -0.92
     feroit
    -0.91
     imprimée
    -0.91
     vectorielle
    -0.90
     obesity
    -0.88
     overweight
    -0.88
    POSITIVE LOGITS
    ness
    0.77
    s
    0.72
    ing
    0.70
    er
    0.60
    ly
    0.57
    -
    0.57
    ry
    0.56
    ми
    0.52
     lat
    0.52
    sic
    0.52
    Activations Density 0.604%

    No Known Activations