© 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. 95106
    Prev
    Next
    INDEX
    Explanations

    maintain

    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
    BufferException
    -0.53
    bewerken
    -0.49
    rativa
    -0.48
    GEBURTS
    -0.48
    engelsk
    -0.48
    rdı
    -0.48
    empio
    -0.47
    UserScript
    -0.46
    useEffect
    -0.46
    worse
    -0.46
    POSITIVE LOGITS
     itself
    0.60
     themselves
    0.59
     Itself
    0.55
     haki
    0.52
     ourselves
    0.52
    complexContent
    0.52
     himself
    0.52
    #+#
    0.49
     homeostasis
    0.48
    apolis
    0.48
    Activations Density 0.002%

    No Known Activations