© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92513
    Prev
    Next
    INDEX
    Explanations

    General

    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
     General
    -1.02
     Conservation
    -0.97
    conservation
    -0.93
    Conservation
    -0.88
    General
    -0.85
     conservation
    -0.84
    general
    -0.84
     general
    -0.84
     CONSERVATION
    -0.79
    crollView
    -0.78
    POSITIVE LOGITS
    awtextra
    0.58
    ist
    0.57
    ion
    0.56
    iv
    0.55
    ed
    0.53
    st
    0.50
    ism
    0.48
    Hentet
    0.48
    ore
    0.48
    ConstraintMaker
    0.48
    Activations Density 0.816%

    No Known Activations