© 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. 12182
    Prev
    Next
    INDEX
    Explanations

    legal/technical mixed texts

    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
     citizens
    -0.61
    citizens
    -0.57
     Citizens
    -0.52
    UnsafeEnabled
    -0.52
    Citizens
    -0.50
     TestBed
    -0.50
     citizen
    -0.49
     ciudadanía
    -0.49
     Citizen
    -0.48
     Bourgoin
    -0.48
    POSITIVE LOGITS
     незавершена
    0.63
     lèvres
    0.63
    TagMode
    0.60
     متعلقه
    0.57
    躇
    0.56
    انيف
    0.55
    ages
    0.55
    andidaten
    0.54
    edi
    0.53
    etsk
    0.53
    Activations Density 0.046%

    No Known Activations