© 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. 1-CLT-HP
    7. 10424
    Prev
    Next
    INDEX
    Explanations

    a/an

    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
     يتيمه
    -0.93
     disambiguazione
    -0.88
     الرياضيه
    -0.84
     NSCoder
    -0.82
    featureID
    -0.82
    \{\\
    -0.80
     &___
    -0.80
     ExecuteAsync
    -0.79
    حياته
    -0.78
    enumii
    -0.78
    POSITIVE LOGITS
     variety
    0.84
     combination
    0.69
     mixture
    0.64
     range
    0.62
     technique
    0.58
     type
    0.57
     variedade
    0.57
     different
    0.57
     mix
    0.56
     form
    0.55
    Activations Density 0.042%

    No Known Activations