© 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. 5679
    Prev
    Next
    INDEX
    Explanations

    apostrophe

    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
    RenderAtEndOf
    -0.91
    expandindo
    -0.90
    +#+#
    -0.86
    InvalidProtocol
    -0.83
    contentLoaded
    -0.83
    anolamine
    -0.79
    IndentedString
    -0.78
    Diweddarwch
    -0.78
    consulté
    -0.77
    argout
    -0.75
    POSITIVE LOGITS
    ’
    0.57
    ↵↵
    0.53
    ‍
    0.52
     by
    0.50
    '
    0.48
    <em>
    0.45
    Referanser
    0.45
    Related
    0.42
     to
    0.42
     on
    0.42
    Activations Density 0.002%

    No Known Activations