© 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. 72881
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions

    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
     tantum
    -0.50
    atorship
    -0.48
    CrossRef
    -0.47
     sœur
    -0.47
     klok
    -0.46
     trasparente
    -0.46
     vastaan
    -0.46
     popoli
    -0.45
     culturel
    -0.44
    tığı
    -0.44
    POSITIVE LOGITS
    TestingModule
    0.64
    PasswordEncoder
    0.56
    InputBorder
    0.55
     cetera
    0.52
     Wes
    0.50
     Cats
    0.49
     Euclid
    0.49
     Alco
    0.49
     Buda
    0.49
     do
    0.49
    Activations Density 0.001%

    No Known Activations