© 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. 5-CLT-HP
    7. 5619
    Prev
    Next
    INDEX
    Explanations

    science

    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
    Gu
    -0.45
     gu
    -0.45
     Penal
    -0.44
     Chance
    -0.44
     telef
    -0.43
    Ran
    -0.42
     geluk
    -0.42
    LogLevel
    -0.42
     agricoles
    -0.41
    zeczytaj
    -0.41
    POSITIVE LOGITS
     שוליים
    0.85
     AssemblyCulture
    0.81
    tagHelperRunner
    0.81
    Geplaatst
    0.77
    featureID
    0.77
     Normdatei
    0.75
     kasarigan
    0.71
     كومونز
    0.69
    ValueStyle
    0.68
    SourceChecksum
    0.66
    Activations Density 0.000%

    No Known Activations