© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 675
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Infórmanos
    -0.60
     save
    -0.57
     to
    -0.54
     bring
    -0.52
     try
    -0.50
    PositiveButton
    -0.49
     make
    -0.47
     secure
    -0.46
     garant
    -0.46
     come
    -0.46
    POSITIVE LOGITS
    OGND
    0.79
     Efq
    0.74
     ſever
    0.73
    LookAnd
    0.72
     ſeveral
    0.71
    DockStyle
    0.70
     ModelRenderer
    0.68
     snippetHide
    0.68
    dafx
    0.67
     dafs
    0.66
    Activations Density 0.003%

    No Known Activations