© 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. 4-CLT-HP
    7. 73
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     <<<<<<<<<<<<<<
    -0.90
     createState
    -0.73
     Мексичка
    -0.70
     CommonModule
    -0.68
    PyTuple
    -0.66
     transférez
    -0.66
    SequentialGroup
    -0.65
     Paglinawan
    -0.65
     ModelExpression
    -0.65
    windowFixed
    -0.64
    POSITIVE LOGITS
     éclair
    0.48
     strike
    0.46
    strike
    0.43
    crossed
    0.42
     Strike
    0.42
    ytä
    0.41
    Strike
    0.41
    ersonic
    0.41
    pitched
    0.40
     express
    0.39
    Activations Density 0.026%

    No Known Activations