© 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. 5-CLT-HP
    7. 5865
    Prev
    Next
    INDEX
    Explanations

    util

    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
    AsUp
    -0.62
    errHandler
    -0.60
     kasarigan
    -0.47
    Brainz
    -0.47
    joba
    -0.46
    ritation
    -0.45
    entuk
    -0.45
    ">//
    -0.45
     Sequelize
    -0.45
    transQ
    -0.44
    POSITIVE LOGITS
     kaarangay
    0.74
    MLLoader
    0.56
    doing
    0.56
     نس
    0.54
     doing
    0.52
    hasError
    0.50
     invokingState
    0.49
     done
    0.49
    Gruß
    0.49
    Doing
    0.49
    Activations Density 0.010%

    No Known Activations