© 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. 5-CLT-HP
    7. 2884
    Prev
    Next
    INDEX
    Explanations

    court cases and item numbers

    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
    mer
    -0.41
    so
    -0.41
    rungsseite
    -0.38
    agg
    -0.37
    CDs
    -0.37
    ArgsConstructor
    -0.36
    ă
    -0.36
    Zed
    -0.35
    vo
    -0.35
    z
    -0.34
    POSITIVE LOGITS
     reaſon
    0.75
     myſelf
    0.73
     pleaſure
    0.71
     reafon
    0.67
     Efq
    0.66
     occafion
    0.66
     fhort
    0.66
     صوتيه
    0.65
    iffion
    0.65
    ↵
    0.65
    Activations Density 0.002%

    No Known Activations