© 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. 3182
    Prev
    Next
    INDEX
    Explanations

    predict

    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
     الحره
    -0.73
    })).
    -0.72
    <eos>
    -0.69
    <bos>
    -0.67
    ))).
    -0.66
    '.
    -0.65
    ''.
    -0.64
    Autoritní
    -0.61
     ```
    -0.60
    ʺ
    -0.60
    POSITIVE LOGITS
    ,
    0.59
     –
    0.56
     that
    0.48
    tvguidetime
    0.45
     -
    0.44
     so
    0.44
     it
    0.43
    ortment
    0.42
    DTD
    0.38
    があるので
    0.37
    Activations Density 0.132%

    No Known Activations