© 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. 15403
    Prev
    Next
    INDEX
    Explanations

    9

    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
    9
    -1.23
     ninety
    -0.93
     nine
    -0.88
    ⁹
    -0.84
     Ninety
    -0.83
    ９
    -0.83
     NINE
    -0.77
    nine
    -0.76
     Ninth
    -0.76
     nueve
    -0.75
    POSITIVE LOGITS
    IsContent
    0.55
    cmath
    0.52
     برانيه
    0.52
     />';
    0.52
     "";
    0.51
     Lon
    0.51
    WireFormatLite
    0.50
    addContainerGap
    0.50
    tvguidetime
    0.50
     Eng
    0.49
    Activations Density 0.065%

    No Known Activations