© 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. 94398
    Prev
    Next
    INDEX
    Explanations

    conjunctions/punctuation

    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
    =$?
    -0.65
    fromnode
    -0.61
     Inscrivez
    -0.57
    )";
    -0.56
     MenuView
    -0.56
    %");
    -0.56
     Púb
    -0.55
     vectoriales
    -0.54
     nahilalakip
    -0.54
    %";
    -0.52
    POSITIVE LOGITS
     felt
    0.58
     Ty
    0.56
    queryInterface
    0.56
    AxisAlignment
    0.56
    migrationBuilder
    0.54
    felt
    0.53
    makeConstraints
    0.52
    DeleteBehavior
    0.52
    ulite
    0.51
    Ty
    0.51
    Activations Density 0.002%

    No Known Activations