© 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. 5473
    Prev
    Next
    INDEX
    Explanations

    formal documents

    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
    Rptr
    -0.43
    idjan
    -0.42
    umpf
    -0.41
     Modelle
    -0.41
    QObject
    -0.41
    featureID
    -0.40
    ⓧ
    -0.40
    ;
    -0.40
     respectively
    -0.39
     tracks
    -0.39
    POSITIVE LOGITS
    TagMode
    0.84
    queryInterface
    0.69
    IntoConstraints
    0.66
     />";
    0.65
    />";
    0.65
    原始内容存档于
    0.64
     <>",
    0.63
     Архів
    0.62
    "])){
    0.62
    fjspx
    0.61
    Activations Density 0.005%

    No Known Activations