© 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. 5-CLT-HP
    7. 92212
    Prev
    Next
    INDEX
    Explanations

    enough

    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
     sought
    -0.52
    ჭ
    -0.49
     wasted
    -0.48
    ibase
    -0.48
    KommentareTeilen
    -0.47
    awtextra
    -0.46
     Mena
    -0.46
     promoted
    -0.46
    Clik
    -0.45
    mehr
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.68
    uxxxx
    0.68
    +#+#
    0.67
    istoitu
    0.63
    adaptiveStyles
    0.61
    Erreferentziak
    0.61
    enderror
    0.59
     carve
    0.57
    horabuena
    0.56
    FormTagHelper
    0.55
    Activations Density 0.001%

    No Known Activations