© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41486
    Prev
    Next
    INDEX
    Explanations

    launcher

    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
     betweenstory
    -1.23
     photolibrary
    -1.07
     الحره
    -1.02
     $_"
    -1.02
     Efq
    -0.96
    ItemBackground
    -0.96
     Forumite
    -0.95
     Majefty
    -0.94
     itſelf
    -0.94
    sterious
    -0.91
    POSITIVE LOGITS
     for
    0.60
     
    0.57
     For
    0.56
     to
    0.52
     (
    0.51
    For
    0.50
     From
    0.48
     all
    0.47
    <eos>
    0.47
     e
    0.47
    Activations Density 0.560%

    No Known Activations