© 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. 92132
    Prev
    Next
    INDEX
    Explanations

    engraver

    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
     engraver
    -1.36
     Mariner
    -1.12
     purpoſe
    -0.93
     pleaſure
    -0.88
     greateſt
    -0.84
     ſtate
    -0.84
     reaſon
    -0.84
     Mariners
    -0.80
     myſelf
    -0.79
     fubject
    -0.77
    POSITIVE LOGITS
    ing
    0.60
    o
    0.54
    of
    0.50
    i
    0.48
     charging
    0.46
    s
    0.45
    ########.
    0.45
    a
    0.45
    char
    0.44
     successfully
    0.44
    Activations Density 0.135%

    No Known Activations