© 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. 44185
    Prev
    Next
    INDEX
    Explanations

    came/became

    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
     Efq
    -1.01
     went
    -0.98
     grew
    -0.98
     avoient
    -0.97
     took
    -0.96
     became
    -0.96
     came
    -0.94
     ―――――
    -0.91
     feroit
    -0.90
     showed
    -0.90
    POSITIVE LOGITS
     the
    1.12
     a
    1.06
     
    0.96
    <eos>
    0.95
     an
    0.90
    ↵
    0.86
     to
    0.81
    ...
    0.81
    …
    0.81
     "
    0.80
    Activations Density 0.181%

    No Known Activations