© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3277
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific text snippets

    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
     Mobile
    -0.52
     AssemblyCulture
    -0.49
     Fire
    -0.48
     ISNI
    -0.48
    typer
    -0.48
    itur
    -0.47
     numberWith
    -0.47
    sky
    -0.46
    ivet
    -0.46
     Deal
    -0.46
    POSITIVE LOGITS
    sizeCache
    0.61
     незавершена
    0.61
    ReusableCell
    0.60
    StoryboardSegue
    0.60
    ensement
    0.60
     lenker
    0.59
    IntoConstraints
    0.59
    centralwidget
    0.59
    EndGlobalSection
    0.59
     विश्वसनीयता
    0.58
    Activations Density 0.003%

    No Known Activations