© 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. 0-CLT-HP
    7. 94335
    Prev
    Next
    INDEX
    Explanations

    knockout

    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
     الحره
    -0.66
     mắn
    -0.62
    ed
    -0.61
     refroid
    -0.59
     بيها
    -0.58
     rollout
    -0.58
    ngrx
    -0.57
    ategorias
    -0.56
     Hedgehog
    -0.56
     Skies
    -0.56
    POSITIVE LOGITS
     kasarigan
    0.60
    :✨
    0.59
    Lähteet
    0.54
     EClass
    0.50
    BeginInit
    0.46
    Soma
    0.46
     Perſ
    0.44
    OrNil
    0.44
     Antropo
    0.43
    感受
    0.43
    Activations Density 1.782%

    No Known Activations