© 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. 0-CLT-HP
    7. 95289
    Prev
    Next
    INDEX
    Explanations

    lattice

    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
     ſtate
    -0.80
     démocr
    -0.79
     réguli
    -0.77
     chré
    -0.77
     définiti
    -0.75
     anún
    -0.73
     gomma
    -0.73
    berdayakan
    -0.73
     sabbia
    -0.73
     samfun
    -0.71
    POSITIVE LOGITS
    tagHelperRunner
    0.63
    less
    0.59
    ing
    0.56
    work
    0.56
    ly
    0.55
    :✨
    0.53
    like
    0.52
    ling
    0.51
     OMIT
    0.51
     const
    0.50
    Activations Density 0.401%

    No Known Activations