© 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. 5-CLT-HP
    7. 5647
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Signalez
    -0.76
     handleMessage
    -0.63
    osoba
    -0.58
    ftagPool
    -0.58
    transQ
    -0.57
    tvguidetime
    -0.57
     moindre
    -0.57
     superiori
    -0.56
    лков
    -0.55
     >=",
    -0.55
    POSITIVE LOGITS
     total
    0.93
     number
    0.59
    ölker
    0.58
    yntaxException
    0.56
    total
    0.54
    исленность
    0.54
     "..\..\..\
    0.52
     overall
    0.51
     amount
    0.50
     общей
    0.49
    Activations Density 0.001%

    No Known Activations