© 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. 95270
    Prev
    Next
    INDEX
    Explanations

    Document snippets

    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
     the
    -0.88
    i
    -0.79
    e
    -0.78
     disambiguazione
    -0.71
    ImageContext
    -0.68
    featureID
    -0.66
    events
    -0.65
    yet
    -0.63
     propOrder
    -0.63
    equipment
    -0.62
    POSITIVE LOGITS
    selves
    0.64
     épaules
    0.61
    ership
    0.55
    ness
    0.54
    hesis
    0.54
    aneous
    0.54
    ResumeLayout
    0.53
    alled
    0.52
    bald
    0.52
    iness
    0.50
    Activations Density 0.364%

    No Known Activations