© 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. 0-CLT-HP
    7. 42969
    Prev
    Next
    INDEX
    Explanations

    kind

    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
     kinds
    -1.27
     kind
    -1.17
    kinds
    -0.80
     sorts
    -0.78
    kind
    -0.78
     Kinds
    -0.77
    IContainer
    -0.76
     Kind
    -0.74
     types
    -0.72
     disponibilités
    -0.72
    POSITIVE LOGITS
     of
    0.82
     guste
    0.58
     recombination
    0.56
    ven
    0.52
    anga
    0.51
    ert
    0.50
    ation
    0.50
    ator
    0.49
     lccn
    0.49
    oid
    0.49
    Activations Density 0.087%

    No Known Activations