© 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. 1-CLT-HP
    7. 10600
    Prev
    Next
    INDEX
    Explanations

    z

    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
    y
    -0.47
    Gilla
    -0.46
     hâte
    -0.45
     nahilalakip
    -0.44
     efficaces
    -0.43
     ◄
    -0.42
    Jeografia
    -0.42
     respirar
    -0.41
     noqa
    -0.41
     ModelExpression
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.68
    minipage
    0.63
    maketitle
    0.59
    JNIEnv
    0.57
    ReusableCell
    0.57
     насељу
    0.56
     imageNamed
    0.55
    stonia
    0.54
    cended
    0.54
     ràng
    0.54
    Activations Density 0.009%

    No Known Activations