© 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. 72709
    Prev
    Next
    INDEX
    Explanations

    ??

    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
    <bos>
    -0.73
     verſ
    -0.47
     ſta
    -0.47
     Langer
    -0.47
     ſte
    -0.47
     ſch
    -0.46
     Verſ
    -0.46
    λοι
    -0.46
     ſtate
    -0.46
     Llew
    -0.46
    POSITIVE LOGITS
    ThroughAttribute
    0.22
     autorytatywna
    0.19
    //
    0.18
     saites
    0.17
    tanleria
    0.14
    ⓧ
    0.14
     ň
    0.13
     stället
    0.13
     varandra
    0.13
     Мексичка
    0.12
    Activations Density 0.907%

    No Known Activations