© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74621
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Viitteet
    -0.64
     оригіналу
    -0.58
    GOTREF
    -0.54
    BuilderFactory
    -0.53
    offsetof
    -0.49
    __;
    -0.47
     Fow
    -0.47
    tagext
    -0.47
    وعة
    -0.47
    новништво
    -0.46
    POSITIVE LOGITS
    +#+#
    0.62
    цездатний
    0.59
     Autorizaciones
    0.53
     VIAF
    0.49
    TestingModule
    0.49
    য়ে
    0.49
     Finlay
    0.48
    estor
    0.47
     eth
    0.47
     elegans
    0.46
    Activations Density 0.002%

    No Known Activations