© 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. 1-CLT-HP
    7. 15109
    Prev
    Next
    INDEX
    Explanations

    Document excerpts

    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
     pamphlets
    -0.86
     pamphlet
    -0.83
    StoryboardSegue
    -0.82
     Pamph
    -0.70
     Pamphlet
    -0.66
    irectional
    -0.63
     Babylonian
    -0.61
    CodeAttribute
    -0.59
    yntaxException
    -0.58
     nahilalakip
    -0.56
    POSITIVE LOGITS
    AddHtmlAttribute
    0.45
    fortawesome
    0.45
    ביוגרפיה
    0.44
    enumi
    0.44
    سطس
    0.44
    {}".
    0.40
    raisemb
    0.40
     الحره
    0.40
     acho
    0.39
     createState
    0.39
    Activations Density 0.003%

    No Known Activations