© 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. 91154
    Prev
    Next
    INDEX
    Explanations

    wasn

    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
    was
    -2.05
    Was
    -1.92
     Was
    -1.75
     wasn
    -1.64
    wasn
    -1.61
     was
    -1.52
     Wasn
    -1.46
     wasnt
    -1.35
    Wasn
    -1.35
     WAS
    -1.25
    POSITIVE LOGITS
     the
    0.57
    rophilic
    0.52
     a
    0.50
     sind
    0.48
    loj
    0.48
    RESH
    0.48
    ieux
    0.47
    ZING
    0.47
    icare
    0.47
    perror
    0.46
    Activations Density 0.331%

    No Known Activations