© 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. 91265
    Prev
    Next
    INDEX
    Explanations

    can

    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
     be
    -0.89
    hyrchwyd
    -0.65
     coû
    -0.62
     endregion
    -0.60
     soyez
    -0.60
    remain
    -0.60
    Javadoc
    -0.59
    RenderAtEndOf
    -0.59
    HEET
    -0.59
     pokrač
    -0.58
    POSITIVE LOGITS
     the
    0.49
     less
    0.45
     a
    0.45
     通販
    0.44
    Rüyada
    0.43
    PickerController
    0.42
    OGND
    0.42
    تقاوى
    0.42
     accountability
    0.42
    Organisateur
    0.42
    Activations Density 0.005%

    No Known Activations