© 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. 93224
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
     concepts
    -1.36
     ideas
    -1.22
    fuls
    -1.18
     itſelf
    -1.09
     aspects
    -1.07
     conceptions
    -1.05
    ſelf
    -1.04
     notions
    -1.03
     facets
    -1.03
     Theſe
    -1.02
    POSITIVE LOGITS
     pouvoirs
    0.59
     for
    0.58
     of
    0.57
     that
    0.57
     like
    0.56
     are
    0.56
     larmes
    0.56
     lèvres
    0.54
     demás
    0.50
     oreilles
    0.50
    Activations Density 1.627%

    No Known Activations