© 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. 98040
    Prev
    Next
    INDEX
    Explanations

    severe

    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
     الرياضيه
    -0.85
     médicaux
    -0.74
     كومونز
    -0.71
    rungsseite
    -0.68
    aarrggbb
    -0.67
     médicale
    -0.66
    Personendaten
    -0.65
    Cyfeiriadau
    -0.64
     تانيه
    -0.64
    enderror
    -0.63
    POSITIVE LOGITS
     reductions
    0.52
     top
    0.50
     declines
    0.50
     drops
    0.48
     decreases
    0.48
     under
    0.48
    Redirection
    0.47
     Underwood
    0.47
     over
    0.46
     fluctuations
    0.46
    Activations Density 0.002%

    No Known Activations