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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42918
    Prev
    Next
    INDEX
    Explanations

    behalf

    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
     Normdatei
    -1.02
     behalf
    -1.02
     recently
    -1.01
     relation
    -0.98
    recently
    -0.98
     regards
    -0.96
     recientemente
    -0.90
     lately
    -0.90
     récemment
    -0.90
     auffi
    -0.88
    POSITIVE LOGITS
    <bos>
    0.66
    ↵↵
    0.59
    aps
    0.52
    ap
    0.44
    ↵
    0.44
     
    0.43
    .
    0.42
    ous
    0.42
    期刊论文
    0.41
    <eos>
    0.41
    Activations Density 0.075%

    No Known Activations