© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4545
    Prev
    Next
    INDEX
    Explanations

    Various topics

    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
    ək
    -0.62
    مصادر
    -0.55
     trickle
    -0.55
     Commencez
    -0.51
    ########.
    -0.50
     trolley
    -0.48
    stool
    -0.47
    unsqueeze
    -0.45
     Backward
    -0.45
    ThemeOverlay
    -0.45
    POSITIVE LOGITS
    abestanden
    0.76
    Skocz
    0.75
     تانيه
    0.74
    VersionUID
    0.72
    Rhestr
    0.70
    BeginContext
    0.69
     StatefulWidget
    0.66
    Wide
    0.65
     entier
    0.65
    modb
    0.64
    Activations Density 0.033%

    No Known Activations