© 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. 20-CLT-HP
    7. 72443
    Prev
    Next
    INDEX
    Explanations

    apolog

    np_max-act-logits · 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
     kasarigan
    -0.59
    ondissement
    -0.55
     Adu
    -0.47
     gild
    -0.47
    Par
    -0.46
     par
    -0.45
     Par
    -0.45
     ruines
    -0.44
     ad
    -0.43
    :=
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.82
    StoryboardSegue
    0.66
    ArrowToggle
    0.65
    出版年
    0.65
    ItemBackground
    0.65
    #+#
    0.63
     Wikimedijinoj
    0.60
     <=",
    0.58
     <>",
    0.57
    MessageTagHelper
    0.57
    Activations Density 0.001%

    No Known Activations