© 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. 98000
    Prev
    Next
    INDEX
    Explanations

    actions to change something

    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
    RectangleBorder
    -0.67
     ujednoznacz
    -0.59
     perchance
    -0.54
    참고
    -0.54
    Past
    -0.54
    __":
    -0.53
     QtCore
    -0.53
    ViewImports
    -0.52
     nutmeg
    -0.52
    ctive
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.54
    сылкі
    0.49
    /***/
    0.48
    页面存档备份
    0.46
    Története
    0.45
    แค่
    0.45
     GenerationType
    0.45
    kussion
    0.45
     للاسماء
    0.44
     autorytatywna
    0.43
    Activations Density 0.007%

    No Known Activations