© 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. 94350
    Prev
    Next
    INDEX
    Explanations

    tragic

    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
     tragic
    -1.32
     tragically
    -1.20
     Trag
    -1.19
    Trag
    -1.16
     tragedy
    -1.03
     tragedies
    -0.95
     ***!
    -0.93
     समीक्षक
    -0.92
     protoimpl
    -0.91
    SourceChecksum
    -0.88
    POSITIVE LOGITS
    ally
    0.80
    als
    0.60
    ent
    0.55
    alia
    0.54
    ale
    0.52
    ude
    0.51
    ated
    0.50
    ks
    0.50
    ured
    0.49
    om
    0.48
    Activations Density 0.688%

    No Known Activations