© 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. 10362
    Prev
    Next
    INDEX
    Explanations

    science

    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
     suelos
    -0.55
     történ
    -0.49
     Namen
    -0.47
    name
    -0.47
     préc
    -0.43
     Namens
    -0.43
    AndEndTag
    -0.41
     اسم
    -0.41
    navn
    -0.41
     idéia
    -0.41
    POSITIVE LOGITS
    +#+#
    0.92
    <bos>
    0.92
    AddTagHelper
    0.87
     '\\;'
    0.87
    IndentedString
    0.80
    ConstraintMaker
    0.73
     GenerationType
    0.72
     autorytatywna
    0.72
    Identyfik
    0.70
    +:+
    0.70
    Activations Density 0.013%

    No Known Activations