© 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. 565
    Prev
    Next
    INDEX
    Explanations

    general information

    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
    ’
    -0.69
    '
    -0.66
    وفة
    -0.57
    <bos>
    -0.56
     T
    -0.52
     distanciation
    -0.51
    kmal
    -0.50
     referenties
    -0.50
     defaultstate
    -0.50
    详细信息
    -0.50
    POSITIVE LOGITS
     femininas
    0.58
    }>;
    0.57
     kautta
    0.56
     asti
    0.55
    Hochspringen
    0.55
     betrekking
    0.52
     générations
    0.52
    :​
    0.52
     .;
    0.51
    즉
    0.50
    Activations Density 0.002%

    No Known Activations