© 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. 5-CLT-HP
    7. 93856
    Prev
    Next
    INDEX
    Explanations

    At a point in time

    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
    anskje
    -0.63
    ształ
    -0.52
    cuno
    -0.50
    Somewhere
    -0.49
    某个
    -0.48
    erdere
    -0.48
     Somewhere
    -0.47
    MaxValue
    -0.46
    ardless
    -0.46
     öfter
    -0.46
    POSITIVE LOGITS
     Roskov
    0.78
    NameInMap
    0.71
    ---*/
    0.66
     AssemblyTitle
    0.61
    TestTools
    0.60
     MenuView
    0.59
     مشين
    0.59
    typeorm
    0.57
    RTEE
    0.57
     Meksiku
    0.56
    Activations Density 0.007%

    No Known Activations