© 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. 42847
    Prev
    Next
    INDEX
    Explanations

    working

    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
     working
    -2.06
    working
    -2.03
    Working
    -1.93
     Working
    -1.89
     WORKING
    -1.75
    WORKING
    -1.63
     worked
    -1.59
     Worked
    -1.45
    Worked
    -1.43
    worked
    -1.34
    POSITIVE LOGITS
     on
    0.65
    .
    0.62
     for
    0.60
     in
    0.50
    ,
    0.50
     with
    0.49
    i
    0.49
     from
    0.45
     en
    0.45
    </sub>
    0.44
    Activations Density 0.692%

    No Known Activations