© 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. 45620
    Prev
    Next
    INDEX
    Explanations

    sports

    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
    IsContent
    -0.97
    :✨
    -0.96
    enterOuterAlt
    -0.90
    parsedMessage
    -0.89
     désolés
    -0.89
    setVerticalGroup
    -0.88
    +#+#
    -0.85
     <<<<<<<<<<<<<<
    -0.85
     مشين
    -0.84
    localctx
    -0.81
    POSITIVE LOGITS
     preferencias
    0.42
     Worms
    0.41
     orta
    0.40
     Pública
    0.40
    cis
    0.39
     pettico
    0.39
     consciously
    0.38
    tica
    0.38
    bw
    0.38
     Correctional
    0.38
    Activations Density 0.016%

    No Known Activations