© 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. 1-CLT-HP
    7. 10239
    Prev
    Next
    INDEX
    Explanations

    buster

    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
     Pied
    -0.44
     bit
    -0.41
    ніципа
    -0.41
     odkazy
    -0.39
     Photocase
    -0.39
    bit
    -0.39
     الحره
    -0.38
    scores
    -0.38
    publish
    -0.37
    cluse
    -0.37
    POSITIVE LOGITS
    ništ
    0.82
    MetaObject
    0.77
    SequentialGroup
    0.76
    AccessorTable
    0.66
    CopyWith
    0.65
     }{@
    0.64
     makeStyles
    0.64
    Jereo
    0.60
     requestCode
    0.60
    ыгана
    0.60
    Activations Density 0.034%

    No Known Activations