© 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. 42986
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     spot
    -1.11
    spot
    -1.04
     Spot
    -0.98
    Spot
    -0.98
     endforeach
    -0.92
     ModelExpression
    -0.88
     spotted
    -0.86
     незавершена
    -0.84
     rayures
    -0.83
     déchir
    -0.82
    POSITIVE LOGITS
     material
    0.45
     or
    0.45
    IBarButtonItem
    0.43
     protein
    0.41
     int
    0.40
     S
    0.40
     which
    0.40
    Set
    0.39
     and
    0.39
     sets
    0.39
    Activations Density 0.395%

    No Known Activations