© 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. 77560
    Prev
    Next
    INDEX
    Explanations

    synonyms for "known"

    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
     المعيارى
    -1.13
    tagHelperRunner
    -0.98
    IUrlHelper
    -0.93
    ftagPool
    -0.91
    انيف
    -0.91
    TestingModule
    -0.88
    ValueStyle
    -0.87
     Roskov
    -0.81
     disambiguazione
    -0.81
     typelib
    -0.81
    POSITIVE LOGITS
     known
    0.63
     real
    0.52
    Known
    0.52
    known
    0.48
    ständ
    0.43
     total
    0.42
     connu
    0.41
     recognized
    0.41
     Known
    0.41
     sure
    0.38
    Activations Density 0.000%

    No Known Activations