© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    committed dedicated

    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
    harusnya
    -0.59
     snippetHide
    -0.59
    Portail
    -0.57
    Bretagne
    -0.57
     kasarigan
    -0.55
     AssemblyTitle
    -0.54
     volontà
    -0.52
    pinMode
    -0.52
    ########.
    -0.52
    meanor
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.62
     to
    0.60
    oredCriteria
    0.56
    mergeFrom
    0.51
    cshtml
    0.51
    êu
    0.47
    protoc
    0.47
    ToMove
    0.46
    apimachinery
    0.46
    unknownFields
    0.44
    Activations Density 0.012%

    No Known Activations