© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1994
    Prev
    Next
    INDEX
    Explanations

    sickle

    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
     Monfieur
    -0.96
     houſe
    -0.93
     ſtate
    -0.86
     ſche
    -0.85
     purpoſe
    -0.84
     reaſon
    -0.84
     Chriftian
    -0.83
     Reſ
    -0.82
     ſtand
    -0.81
     ſtre
    -0.81
    POSITIVE LOGITS
    "]]
    0.73
    ist
    0.73
    ed
    0.68
    ")))
    0.67
    ]</
    0.66
    s
    0.65
    ian
    0.64
    ]')
    0.63
    em
    0.61
    iane
    0.60
    Activations Density 0.058%

    No Known Activations