© 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. 688
    Prev
    Next
    INDEX
    Explanations

    only

    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
    InstrumentedTest
    -0.56
    ActionCreators
    -0.54
    ,:,
    -0.53
     Hald
    -0.53
     Roskov
    -0.52
     rapt
    -0.52
    '}>
    -0.52
    pores
    -0.51
     xanth
    -0.51
    HttpHeaders
    -0.50
    POSITIVE LOGITS
     humanas
    0.57
     naturelles
    0.55
     découver
    0.55
     humaines
    0.53
     próprios
    0.52
     réguli
    0.52
     normaux
    0.52
     blessés
    0.52
     ExecuteAsync
    0.51
    GHIJKLM
    0.51
    Activations Density 0.015%

    No Known Activations