© 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. 295
    Prev
    Next
    INDEX
    Explanations

    which that

    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
    folding
    -0.62
    ագրություններ
    -0.62
     Folding
    -0.61
    GEBURTSDATUM
    -0.61
    Folding
    -0.61
     resourceCulture
    -0.59
    folds
    -0.59
    ArgsConstructor
    -0.59
    脚注の使い方
    -0.57
    annels
    -0.56
    POSITIVE LOGITS
     affected
    0.66
     left
    0.56
     lasted
    0.55
     wiped
    0.54
     damaged
    0.54
     saw
    0.54
     destroyed
    0.54
     impacted
    0.54
    elemField
    0.53
     started
    0.52
    Activations Density 0.008%

    No Known Activations