© 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. 9112
    Prev
    Next
    INDEX
    Explanations

    Hard time

    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
     defaultstate
    -0.82
    mybatisplus
    -0.78
     Waray
    -0.73
    avax
    -0.67
    iecie
    -0.66
    UIControlState
    -0.66
     HasFactory
    -0.64
     विश्वसनीयता
    -0.63
    createCanvas
    -0.61
    AutoresizingMask
    -0.60
    POSITIVE LOGITS
     Reform
    0.47
    LookAnd
    0.46
    tonode
    0.45
    epam
    0.45
    InitVars
    0.44
    فران
    0.44
     kaki
    0.43
     conduc
    0.41
     Road
    0.41
     négoci
    0.40
    Activations Density 0.015%

    No Known Activations