© 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. 98206
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
     beauty
    -0.65
    RenderAtEndOf
    -0.61
     tracking
    -0.57
     visual
    -0.56
     looks
    -0.56
     look
    -0.54
     onCreateView
    -0.53
     LOOK
    -0.52
    akon
    -0.49
     VISUAL
    -0.49
    POSITIVE LOGITS
     nahilalakip
    0.83
    IVEREF
    0.66
    EndContext
    0.66
    homonymie
    0.66
     Roskov
    0.65
    OGND
    0.64
     незавершена
    0.60
     للمعارف
    0.59
     ErrIntOverflow
    0.59
    featureID
    0.59
    Activations Density 0.002%

    No Known Activations