© 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. 72581
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    RectangleBorder
    -0.77
    SpringRunner
    -0.70
     snippetHide
    -0.65
     незавершена
    -0.65
    OGND
    -0.63
    InstrumentedTest
    -0.61
     Quatre
    -0.61
    ographed
    -0.60
    Chham
    -0.60
    __":
    -0.59
    POSITIVE LOGITS
     deli
    0.51
     eff
    0.50
     AspNetCore
    0.47
    win
    0.46
     déco
    0.46
     Hey
    0.46
    っこう
    0.45
    caps
    0.45
    cap
    0.44
    żdy
    0.44
    Activations Density 0.000%

    No Known Activations