© 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. 5-CLT-HP
    7. 94798
    Prev
    Next
    INDEX
    Explanations

    exercise

    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
    tvguidetime
    -0.71
     تانيه
    -0.63
    StructEnd
    -0.58
    ramienta
    -0.56
    VersionUID
    -0.56
    Хьажоргаш
    -0.56
    DeleteBehavior
    -0.56
    FormBorderStyle
    -0.54
    diyesi
    -0.54
    tomatik
    -0.54
    POSITIVE LOGITS
     بيها
    0.57
    es
    0.46
    Previews
    0.46
    DebuggerNonUser
    0.45
    bane
    0.44
     mentiras
    0.42
     bouwen
    0.42
    libft
    0.42
     CreateTagHelper
    0.40
    memoized
    0.40
    Activations Density 0.001%

    No Known Activations