© 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. 20-CLT-HP
    7. 72947
    Prev
    Next
    INDEX
    Explanations

    say "az ending"

    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
    LayoutStyle
    -0.49
    sidemargin
    -0.45
     strtok
    -0.43
    Klar
    -0.43
    ades
    -0.40
    hesus
    -0.39
    ]")]
    -0.39
    UnusedPrivate
    -0.39
     himo
    -0.37
    ącz
    -0.37
    POSITIVE LOGITS
    enumii
    0.81
    enumi
    0.77
     autorytatywna
    0.75
     препратки
    0.73
    phosa
    0.54
     незавершена
    0.54
     BoxDecoration
    0.52
    الإنجليزية
    0.49
    wana
    0.49
     ExecuteAsync
    0.49
    Activations Density 0.001%

    No Known Activations