© 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. 71695
    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
     autorytatywna
    -0.58
    +#+
    -0.56
     &___
    -0.56
    argout
    -0.53
    Slf
    -0.52
     calendriers
    -0.48
     puissiez
    -0.48
    AndEndTag
    -0.45
    VideoCapture
    -0.45
    Décès
    -0.44
    POSITIVE LOGITS
     snippetHide
    0.61
    tagHelperRunner
    0.57
     dynasty
    0.54
    enderror
    0.54
     Übersetzungen
    0.53
     käns
    0.52
     numberOfRows
    0.52
    GridItem
    0.52
    {/
    0.51
     stí
    0.51
    Activations Density 0.004%

    No Known Activations