© 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. 1-CLT-HP
    7. 14733
    Prev
    Next
    INDEX
    Explanations

    mucosa

    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
    NOPQRST
    -0.74
    URBANA
    -0.71
     AssemblyVersion
    -0.69
    brainly
    -0.69
     AssemblyProduct
    -0.65
    lidays
    -0.65
     Autorisations
    -0.65
     @"/
    -0.65
    URLException
    -0.64
    bewerken
    -0.63
    POSITIVE LOGITS
     are
    0.60
    สง
    0.47
     want
    0.47
     tarko
    0.46
    Digitized
    0.44
    izable
    0.44
     looking
    0.43
     ever
    0.42
    if
    0.42
     have
    0.42
    Activations Density 0.046%

    No Known Activations