© 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. 94277
    Prev
    Next
    INDEX
    Explanations

    ability

    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
    -0.90
     whoſe
    -0.83
     Majefty
    -0.82
     depositphotos
    -0.80
     Jefus
    -0.78
     purpoſe
    -0.77
     ſeveral
    -0.76
     pleaſure
    -0.73
     itſelf
    -0.73
     raiſ
    -0.73
    POSITIVE LOGITS
     of
    0.65
    GOTREF
    0.46
     bate
    0.44
     to
    0.43
     blink
    0.39
     cuk
    0.39
     use
    0.38
    GetMapping
    0.38
    ковь
    0.38
    AddTagHelper
    0.37
    Activations Density 0.087%

    No Known Activations