© 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. 92129
    Prev
    Next
    INDEX
    Explanations

    from

    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
    تقاوى
    -0.66
     and
    -0.65
    parsedMessage
    -0.64
    /**
    -0.63
    ArrowToggle
    -0.57
     intptr
    -0.56
     consultato
    -0.56
    just
    -0.56
    fromnode
    -0.54
    ieteur
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.60
     volcanoes
    0.52
     flavour
    0.52
     continúas
    0.50
     flavours
    0.50
     colours
    0.50
    országban
    0.49
    ınca
    0.49
    cèse
    0.48
     axe
    0.48
    Activations Density 0.004%

    No Known Activations