© 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. 45091
    Prev
    Next
    INDEX
    Explanations

    is

    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
     itſelf
    -1.48
     myſelf
    -1.23
     themſelves
    -1.16
     Majefty
    -1.14
     Jefus
    -1.12
     ſever
    -1.12
     ſche
    -1.11
     himſelf
    -1.10
     reaſon
    -1.09
     houſe
    -1.09
    POSITIVE LOGITS
     super
    0.64
     GONNA
    0.59
     gonna
    0.55
     SUCH
    0.54
     références
    0.53
     Gonna
    0.51
     such
    0.50
     total
    0.49
     ok
    0.49
     SO
    0.49
    Activations Density 0.127%

    No Known Activations