© 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. 71953
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     the
    -1.02
     them
    -0.74
     your
    -0.73
    ReusableCell
    -0.63
    LookAnd
    -0.62
    glTexCoord
    -0.59
    OrBuilder
    -0.58
     it
    -0.57
    DispatchToProps
    -0.57
    significant
    -0.56
    POSITIVE LOGITS
    ագրություններ
    0.52
    #+#
    0.50
    　→
    0.48
     sẻ
    0.48
     mechanically
    0.48
     transférez
    0.47
    There
    0.46
    AddHtmlAttribute
    0.46
    EndGlobalSection
    0.46
     colorir
    0.45
    Activations Density 0.003%

    No Known Activations