© 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. 95120
    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
     Nine
    -1.16
     Ninth
    -1.11
     nine
    -1.04
     ninth
    -1.03
     NINE
    -1.02
    tagHelperRunner
    -0.95
    TypedDataSet
    -0.95
     ninety
    -0.95
     Ninety
    -0.94
    Nine
    -0.93
    POSITIVE LOGITS
    ,
    0.81
    -
    0.78
     and
    0.75
    th
    0.70
    2
    0.69
    4
    0.69
    :
    0.68
    6
    0.68
    5
    0.66
     in
    0.66
    Activations Density 0.485%

    No Known Activations