© 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. 20-CLT-HP
    7. 76792
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · 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
    AndEndTag
    -1.03
    Vidite
    -0.98
    NameInMap
    -0.98
     unknownFields
    -0.91
    MessageTagHelper
    -0.85
    ThroughAttribute
    -0.80
    RenderAtEndOf
    -0.74
    principalColumn
    -0.70
    يكب
    -0.69
    httphttps
    -0.69
    POSITIVE LOGITS
    rophi
    0.69
    razine
    0.65
    testing
    0.65
     least
    0.59
    tune
    0.58
    onal
    0.58
    tests
    0.56
     taches
    0.56
    titud
    0.56
    oning
    0.53
    Activations Density 0.281%

    No Known Activations