© 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. 431
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    printStackTrace
    -0.68
    gonic
    -0.65
    tvguidetime
    -0.63
    SourceChecksum
    -0.60
    󠁢
    -0.59
    posedge
    -0.59
    sizeCache
    -0.58
    contentLoaded
    -0.57
    SBATCH
    -0.56
    --){
    -0.55
    POSITIVE LOGITS
    FieldBuilder
    0.55
     écl
    0.50
     felb
    0.48
    ValueGeneration
    0.47
     témo
    0.47
     écout
    0.47
    Datuak
    0.47
     rumahnya
    0.46
     voici
    0.46
     كومونز
    0.46
    Activations Density 0.007%

    No Known Activations