© 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. 5-CLT-HP
    7. 4472
    Prev
    Next
    INDEX
    Explanations

    of

    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
    DockStyle
    -0.66
    ArrowToggle
    -0.60
    RenderAtEndOf
    -0.59
    StoryboardSegue
    -0.57
     bulunabilir
    -0.55
    textTheme
    -0.55
     msglen
    -0.54
     Administrativna
    -0.54
    MemoryWarning
    -0.53
     Мексичка
    -0.53
    POSITIVE LOGITS
     propOrder
    0.61
     StatefulWidget
    0.60
    ględ
    0.49
     Herzegovina
    0.48
    はじめに
    0.48
    yntaxException
    0.47
    Tonight
    0.47
     CONCENT
    0.47
    يكب
    0.47
     Knob
    0.47
    Activations Density 0.000%

    No Known Activations