© 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. 0-CLT-HP
    7. 94540
    Prev
    Next
    INDEX
    Explanations

    spam or code

    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
     levit
    -0.51
    mobileqq
    -0.49
     B
    -0.47
    gypti
    -0.46
    Източници
    -0.46
     nửa
    -0.46
     I
    -0.44
    arschijnlijk
    -0.44
     b
    -0.42
     El
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.97
    Vidite
    0.78
     Paglinawan
    0.69
    сылкі
    0.67
    MessageOf
    0.65
    webElementXpaths
    0.64
     незавершена
    0.61
    NameInMap
    0.60
    يكب
    0.60
     désolés
    0.59
    Activations Density 1.771%

    No Known Activations