© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    oil

    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
     خارجية
    -0.47
    NonQuery
    -0.45
    beginPath
    -0.42
     identidade
    -0.40
     Durant
    -0.39
     alegria
    -0.39
    liflower
    -0.38
    гда
    -0.38
    Croix
    -0.38
    magin
    -0.37
    POSITIVE LOGITS
     '{@
    0.81
    featureID
    0.73
    phalt
    0.67
    InjectAttribute
    0.64
    SequentialGroup
    0.64
    ⓧ
    0.63
     متعلقه
    0.63
    iecie
    0.63
    /******/
    0.60
    writeFieldEnd
    0.60
    Activations Density 0.093%

    No Known Activations