© 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. 4-CLT-HP
    7. 4813
    Prev
    Next
    INDEX
    Explanations

    know

    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
    addContainerGap
    -0.63
     "-";
    -0.56
     Bemer
    -0.53
    endaftaran
    -0.53
     see
    -0.53
    paž
    -0.52
    іга
    -0.51
     démocratie
    -0.51
     Happens
    -0.51
     suffices
    -0.51
    POSITIVE LOGITS
     intptr
    0.54
     ni
    0.49
    elemField
    0.49
     und
    0.49
    নি
    0.48
     урна
    0.45
    CppMethod
    0.45
    oredCriteria
    0.45
    ^{}
    0.45
     unt
    0.45
    Activations Density 0.000%

    No Known Activations