© 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. 5-CLT-HP
    7. 2116
    Prev
    Next
    INDEX
    Explanations

    many/much

    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
    Хьажоргаш
    -0.46
     of
    -0.45
    gr
    -0.44
    ByExample
    -0.41
    Bundle
    -0.41
     cap
    -0.40
    DateTimeField
    -0.39
    subTitle
    -0.39
     para
    -0.39
    件事
    -0.39
    POSITIVE LOGITS
     gyhoeddwyd
    0.68
     anymore
    0.64
    AndEndTag
    0.63
    delà
    0.62
    setVerticalGroup
    0.61
    PMailer
    0.61
    tymologie
    0.59
    WebVitals
    0.59
     dedans
    0.59
     iNdEx
    0.59
    Activations Density 0.003%

    No Known Activations