© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2522
    Prev
    Next
    INDEX
    Explanations

    and

    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
    others
    -0.40
    Other
    -0.40
     other
    -0.40
     they
    -0.40
    Others
    -0.38
     himself
    -0.38
     vieilles
    -0.37
     altro
    -0.36
     me
    -0.35
    other
    -0.35
    POSITIVE LOGITS
    colgroup
    0.83
    SerializedSize
    0.77
    出版年
    0.76
    RTGC
    0.73
    RTLD
    0.72
    ]--;
    0.71
    offsetof
    0.69
    CppMethod
    0.69
    UnusedPrivate
    0.69
     ویکی‌پدی
    0.66
    Activations Density 0.002%

    No Known Activations