© 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. 93590
    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
    RenderAtEndOf
    -0.83
     مشين
    -0.80
     EClass
    -0.80
    <?
    -0.73
    NOPQRST
    -0.72
    Personensuche
    -0.72
    parsedMessage
    -0.69
     beginnetje
    -0.66
     myſelf
    -0.66
     nahilalakip
    -0.65
    POSITIVE LOGITS
     
    0.59
     the
    0.58
     to
    0.57
     that
    0.56
     choice
    0.56
     choosing
    0.55
     selecting
    0.52
     all
    0.50
     using
    0.49
     clicking
    0.49
    Activations Density 0.001%

    No Known Activations