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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92658
    Prev
    Next
    INDEX
    Explanations

    prolific

    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
     Theſe
    -0.76
     ſeveral
    -0.71
     fevere
    -0.70
     Houſe
    -0.69
     vigorously
    -0.69
     profuse
    -0.69
     profusely
    -0.69
     Jefus
    -0.68
     copious
    -0.67
     itſelf
    -0.66
    POSITIVE LOGITS
    ArrowToggle
    0.63
    <bos>
    0.61
    openzeppelin
    0.59
     useParams
    0.57
    PreInfinity
    0.55
    wakilan
    0.52
    хьтан
    0.50
    PCell
    0.49
    etCode
    0.47
     Familienname
    0.47
    Activations Density 0.225%

    No Known Activations