© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92106
    Prev
    Next
    INDEX
    Explanations

    sufficiency

    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
     enough
    -1.91
    enough
    -1.88
    Enough
    -1.59
     Enough
    -1.58
     genug
    -1.52
     ENOUGH
    -1.50
     genoeg
    -1.47
     sufficient
    -1.36
     suficiente
    -1.35
     amount
    -1.27
    POSITIVE LOGITS
     of
    1.08
     to
    0.85
     for
    0.65
    addPreferredGap
    0.50
    ToRefresh
    0.49
    getElementById
    0.47
     (
    0.46
     or
    0.46
     che
    0.44
     Said
    0.44
    Activations Density 0.036%

    No Known Activations