© 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. 4-CLT-HP
    7. 70
    Prev
    Next
    INDEX
    Explanations

    Code/Technical

    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
    NameInMap
    -0.81
     noDo
    -0.79
    الحياه
    -0.74
     للمعارف
    -0.74
    ngdoc
    -0.73
    AndEndTag
    -0.71
     nahilalakip
    -0.71
    ArrowToggle
    -0.71
    :✨
    -0.68
    StoryboardSegue
    -0.68
    POSITIVE LOGITS
     missione
    0.49
    zkiem
    0.43
    Table
    0.43
    חות
    0.41
     liquido
    0.41
    kitan
    0.41
     sujets
    0.40
    phosphate
    0.40
    фици
    0.40
    jamin
    0.39
    Activations Density 0.001%

    No Known Activations