© 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. 94824
    Prev
    Next
    INDEX
    Explanations

    Proper nouns (names, places)

    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
     Clay
    -0.68
     Clause
    -0.66
    WebVitals
    -0.65
    DrawerToggle
    -0.63
    Clay
    -0.62
     Clauses
    -0.62
    er
    -0.61
     Claus
    -0.59
    ing
    -0.58
    AutoField
    -0.57
    POSITIVE LOGITS
     eventdata
    0.56
    ostom
    0.52
    posit
    0.48
    EMPT
    0.48
    pedes
    0.48
    ohol
    0.48
    iform
    0.47
    kaido
    0.46
     hiér
    0.46
    owsky
    0.46
    Activations Density 1.384%

    No Known Activations