© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13845
    Prev
    Next
    INDEX
    Explanations

    build

    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
     himself
    -0.52
     up
    -0.48
     yourself
    -0.46
     herself
    -0.45
    createObject
    -0.39
    xically
    -0.39
    resti
    -0.38
     '\\;'
    -0.38
    up
    -0.38
    toxicity
    -0.38
    POSITIVE LOGITS
     TextAppearance
    0.74
    apimachinery
    0.73
    rawDesc
    0.71
     transfieras
    0.70
    offsetof
    0.69
    CopyWith
    0.67
    anganese
    0.65
    ArgsConstructor
    0.65
     OFDb
    0.65
    iseite
    0.63
    Activations Density 0.005%

    No Known Activations