© 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. 0-CLT-HP
    7. 45194
    Prev
    Next
    INDEX
    Explanations

    systemic

    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
    ching
    -0.85
    doras
    -0.69
     Systemic
    -0.65
     systemic
    -0.65
     Wikimédia
    -0.59
     systematic
    -0.59
     africains
    -0.59
     optique
    -0.58
    System
    -0.57
     Romains
    -0.57
    POSITIVE LOGITS
    httphttps
    0.71
    IsContent
    0.70
    HtmlAttribute
    0.70
    ]--;
    0.67
    StoreMessageInfo
    0.66
     PublicKey
    0.63
    GEBURTSDATUM
    0.60
    DebuggerStep
    0.60
     fit
    0.60
     SqlCommand
    0.59
    Activations Density 0.164%

    No Known Activations