© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13921
    Prev
    Next
    INDEX
    Explanations

    of

    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
    بوابة
    -0.54
     mukana
    -0.51
    zitter
    -0.51
    argout
    -0.51
    GeneratedCode
    -0.49
    كذا
    -0.49
    leşti
    -0.49
     sanoo
    -0.49
    farwyddwr
    -0.47
    లాలు
    -0.47
    POSITIVE LOGITS
     the
    0.71
     تانيه
    0.71
    aarrggbb
    0.62
    icorn
    0.57
     Them
    0.57
     them
    0.53
    )’
    0.51
    hasMoreElements
    0.51
    obes
    0.51
    Them
    0.50
    Activations Density 0.027%

    No Known Activations