© 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. 72474
    Prev
    Next
    INDEX
    Explanations

    say "."

    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
     متعلقه
    -0.63
    ThemeOverlay
    -0.56
    ävän
    -0.56
    dirkan
    -0.56
    OGND
    -0.53
     Decode
    -0.53
    ämään
    -0.52
     logarith
    -0.52
    ungkan
    -0.52
    cambi
    -0.52
    POSITIVE LOGITS
     M
    0.60
     للمعارف
    0.52
    M
    0.50
     CreateTagHelper
    0.46
    sertation
    0.46
     m
    0.44
    m
    0.44
    سطس
    0.42
     فريبيس
    0.41
     gynhyrchwyd
    0.39
    Activations Density 0.005%

    No Known Activations