© 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. 94784
    Prev
    Next
    INDEX
    Explanations

    mellow

    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
    oo
    -0.57
    ee
    -0.56
    pid
    -0.53
     handen
    -0.47
    بوابة
    -0.47
     anticipation
    -0.46
    campo
    -0.45
    usias
    -0.45
    gunta
    -0.45
     alternativ
    -0.45
    POSITIVE LOGITS
     חיצוניים
    0.71
     transférez
    0.71
     CreateTagHelper
    0.67
     beginnetje
    0.67
     BoxFit
    0.66
     استنادى
    0.66
    ImageContext
    0.65
     StringTokenizer
    0.63
    SharedDtor
    0.63
    enumii
    0.63
    Activations Density 0.139%

    No Known Activations