© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92382
    Prev
    Next
    INDEX
    Explanations

    Future prospects

    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
    i
    -0.93
    e
    -0.92
    aw
    -0.75
    a
    -0.75
    s
    -0.71
    ee
    -0.69
    ed
    -0.65
    er
    -0.65
    ised
    -0.59
    eh
    -0.59
    POSITIVE LOGITS
     שוליים
    0.80
    RenderAtEndOf
    0.68
     незавершена
    0.65
    ErrUnexpectedEOF
    0.60
     transfieras
    0.60
    AutoresizingMask
    0.59
     jsPsych
    0.59
     '\\;'
    0.59
     Somos
    0.57
    IsContent
    0.57
    Activations Density 1.389%

    No Known Activations