© 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. 14698
    Prev
    Next
    INDEX
    Explanations

    business context

    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
     associates
    -0.73
     associate
    -0.61
     onBind
    -0.57
     TestBed
    -0.57
     combineReducers
    -0.56
    ImageContext
    -0.56
    parsedMessage
    -0.52
    BITE
    -0.52
    associate
    -0.52
     Associate
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.68
    bootstrapcdn
    0.68
    SequentialGroup
    0.62
     الحره
    0.60
    gman
    0.57
    enegger
    0.55
    metries
    0.54
    ghum
    0.54
     pumping
    0.51
    lujah
    0.51
    Activations Density 0.272%

    No Known Activations