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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40338
    Prev
    Next
    INDEX
    Explanations

    cross

    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
    rungsseite
    -0.83
    Personensuche
    -0.82
     Roskov
    -0.79
     kasarigan
    -0.76
    ArrowToggle
    -0.74
     crucifix
    -0.73
     Baillargeon
    -0.71
    __":
    -0.70
    DebuggerNonUser
    -0.69
     nakalista
    -0.69
    POSITIVE LOGITS
    step
    0.46
     -
    0.45
    level
    0.44
     enää
    0.44
    show
    0.43
    Contents
    0.43
    point
    0.42
     royaume
    0.42
    s
    0.42
     rajut
    0.42
    Activations Density 0.138%

    No Known Activations