© 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. 494
    Prev
    Next
    INDEX
    Explanations

    ring

    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
    ClientSize
    -0.68
    findpost
    -0.66
     AssemblyProduct
    -0.58
    esModule
    -0.57
     незавершена
    -0.57
     Alexander
    -0.56
    NegativeButton
    -0.56
     hung
    -0.55
    awaiter
    -0.54
     يتيمه
    -0.53
    POSITIVE LOGITS
    étoit
    0.50
     feroit
    0.50
    endpush
    0.50
     réguli
    0.49
     Anſ
    0.49
     ainfi
    0.49
    PARTICIP
    0.46
    ěli
    0.46
     beauté
    0.46
     précision
    0.45
    Activations Density 0.001%

    No Known Activations