© 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. 45238
    Prev
    Next
    INDEX
    Explanations

    science/research

    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
     have
    -1.34
    have
    -1.30
    Have
    -1.16
     Have
    -1.09
     HAVE
    -1.06
    HAVE
    -1.02
    PerformLayout
    -1.02
     jouets
    -0.94
     prochaines
    -0.94
     ferons
    -0.93
    POSITIVE LOGITS
     a
    1.12
     the
    1.02
     an
    1.02
     to
    0.98
     not
    0.94
     no
    0.85
    ,
    0.82
     been
    0.81
     their
    0.78
     now
    0.77
    Activations Density 0.083%

    No Known Activations