© 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. 4-CLT-HP
    7. 1627
    Prev
    Next
    INDEX
    Explanations

    Time references

    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
     décennies
    -0.54
     épaules
    -0.54
    roek
    -0.51
     hombro
    -0.51
     समीक्षाएं
    -0.51
     aastal
    -0.50
     noches
    -0.50
     guerres
    -0.49
     demais
    -0.47
     semaines
    -0.46
    POSITIVE LOGITS
     that
    0.73
     Efq
    0.65
     how
    0.64
     those
    0.64
     someone
    0.64
     some
    0.61
     azy
    0.60
    ingtones
    0.59
     what
    0.59
     dogs
    0.58
    Activations Density 0.013%

    No Known Activations