© 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. 4-CLT-HP
    7. 804
    Prev
    Next
    INDEX
    Explanations

    to/for

    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
    UnusedPrivate
    -0.54
    נגלית
    -0.47
     doch
    -0.46
     الفلك
    -0.45
     smells
    -0.44
     struggling
    -0.44
    BeginContext
    -0.43
     murah
    -0.43
     floating
    -0.42
     aven
    -0.42
    POSITIVE LOGITS
     be
    0.79
     utafitiHapana
    0.79
     hold
    0.70
     remain
    0.65
    CodeAttribute
    0.65
     GetEnumerator
    0.64
     typelib
    0.64
     FetchType
    0.63
     stand
    0.63
     stay
    0.62
    Activations Density 0.006%

    No Known Activations