© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12275
    Prev
    Next
    INDEX
    Explanations

    core

    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
    Core
    -0.63
    core
    -0.57
     core
    -0.56
     fondament
    -0.52
    CORE
    -0.49
     Core
    -0.45
     auxquels
    -0.45
     mogelijk
    -0.45
     censiti
    -0.44
     halbe
    -0.43
    POSITIVE LOGITS
     ligiloj
    0.72
    EndProject
    0.66
     externi
    0.65
    Autoritní
    0.65
    XmlAccessorType
    0.62
    celotti
    0.62
    patine
    0.59
    chatron
    0.59
     biopsy
    0.57
    atellite
    0.57
    Activations Density 0.016%

    No Known Activations