© 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. 20-CLT-HP
    7. 72407
    Prev
    Next
    INDEX
    Explanations

    Prime/Apply

    np_max-act-logits · 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
    ugía
    -0.66
     Knitting
    -0.58
    ToTensor
    -0.57
    Diwedd
    -0.56
     Recording
    -0.55
     Backing
    -0.55
    évaluateur
    -0.55
    addCriterion
    -0.54
     SwitchCompat
    -0.54
     كومونز
    -0.52
    POSITIVE LOGITS
     prime
    0.71
     apply
    0.61
     applies
    0.57
     PRIME
    0.56
    prime
    0.55
     mix
    0.54
     sl
    0.52
     chi̍t
    0.52
    Prime
    0.52
    Apply
    0.49
    Activations Density 0.002%

    No Known Activations