© 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. 9008
    Prev
    Next
    INDEX
    Explanations

    of

    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
     forms
    -0.49
     bentuk
    -0.49
    formats
    -0.48
    kaper
    -0.47
     kaksi
    -0.44
    versions
    -0.44
    tilhe
    -0.44
     Formen
    -0.43
    currencies
    -0.43
     tepat
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.86
     linkovi
    0.73
     الحره
    0.71
    Brainz
    0.69
     attainment
    0.68
    tagHelperRunner
    0.68
    GEBURTSDATUM
    0.67
     ProtoMessage
    0.65
     Egli
    0.65
    +#+#
    0.65
    Activations Density 0.014%

    No Known Activations