© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42431
    Prev
    Next
    INDEX
    Explanations

    contemplate

    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
     Efq
    -0.84
     varandra
    -0.81
     thinkers
    -0.73
     thinker
    -0.72
     amiss
    -0.72
     Clerical
    -0.71
     vocale
    -0.71
     étoient
    -0.71
     meille
    -0.69
     aceea
    -0.69
    POSITIVE LOGITS
    s
    0.63
     int
    0.58
    es
    0.57
    a
    0.56
    y
    0.56
    int
    0.56
    an
    0.55
    Ārējās
    0.54
    ing
    0.53
     gainera
    0.53
    Activations Density 0.084%

    No Known Activations