© 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. 611
    Prev
    Next
    INDEX
    Explanations

    @

    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
     חיצוניים
    -0.50
    ().__
    -0.47
    ost
    -0.45
    idopsis
    -0.44
     Jésus
    -0.44
    ::__
    -0.43
    Skocz
    -0.43
     driven
    -0.42
    amerikan
    -0.42
    Revenir
    -0.42
    POSITIVE LOGITS
    ftagPool
    0.74
    niosek
    0.66
    ViewImports
    0.65
    sphase
    0.61
     financieras
    0.60
    création
    0.59
    wikidata
    0.57
     aidant
    0.54
    ltä
    0.54
     resourceCulture
    0.53
    Activations Density 0.004%

    No Known Activations