© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73258
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     resourceCulture
    -0.90
    HomeAsUpEnabled
    -0.85
    IntoConstraints
    -0.84
     CURIAM
    -0.82
     Taste
    -0.77
     Flavor
    -0.76
     goûts
    -0.75
    WebVitals
    -0.75
     FetchType
    -0.74
    taste
    -0.73
    POSITIVE LOGITS
     t
    0.40
     dess
    0.40
     pro
    0.40
    pto
    0.39
     des
    0.37
    ac
    0.37
     dok
    0.37
    Doo
    0.36
     postal
    0.36
     bul
    0.35
    Activations Density 0.001%

    No Known Activations