© 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. 71682
    Prev
    Next
    INDEX
    Explanations

    Los

    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
     дописавши
    -0.65
    routeProvider
    -0.62
    UnusedPrivate
    -0.60
     ujednoznacz
    -0.59
    BeginContext
    -0.57
    olom
    -0.56
     intptr
    -0.56
    UNGEN
    -0.54
     Roskov
    -0.54
    IContainer
    -0.52
    POSITIVE LOGITS
    InSection
    0.51
     disinf
    0.48
    att
    0.47
    issi
    0.44
    ÓD
    0.43
    ActionBar
    0.43
    Stra
    0.43
    DockStyle
    0.42
    ISM
    0.42
     DISE
    0.41
    Activations Density 0.002%

    No Known Activations