© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92893
    Prev
    Next
    INDEX
    Explanations

    uncommon, scientific words

    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
     nahilalakip
    -0.75
     defaultstate
    -0.68
    (!__
    -0.64
     ostavi
    -0.59
    Personensuche
    -0.58
    addCriterion
    -0.56
    localctx
    -0.56
    EndContext
    -0.55
     насељу
    -0.54
    nose
    -0.52
    POSITIVE LOGITS
    ly
    1.08
    ally
    0.98
    mente
    0.84
    fully
    0.70
    ALLY
    0.62
    tably
    0.60
    arily
    0.57
    LY
    0.56
    ably
    0.56
    ories
    0.55
    Activations Density 0.044%

    No Known Activations