© 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. 1-CLT-HP
    7. 9698
    Prev
    Next
    INDEX
    Explanations

    xml

    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
    xml
    -0.81
     autorytatywna
    -0.63
     considérons
    -0.48
    ジェクト
    -0.48
    Bibliograf
    -0.47
     consultato
    -0.47
     scoping
    -0.45
    avy
    -0.44
    kháu
    -0.44
     Biôgrafia
    -0.43
    POSITIVE LOGITS
    ruptedException
    0.65
    Slf
    0.65
    Espèce
    0.64
    Varint
    0.60
    InitStruct
    0.59
     tartalomajánló
    0.57
    putExtra
    0.57
    ngdoc
    0.57
     Efq
    0.57
    ViewImports
    0.56
    Activations Density 0.025%

    No Known Activations