© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6112
    Prev
    Next
    INDEX
    Explanations

    biographies and appointments

    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
    Negative Logits
    țin
    -0.58
    ţin
    -0.57
    ptăm
    -0.54
    ținut
    -0.47
     nœ
    -0.47
    <bos>
    -0.47
     nvm
    -0.46
     proposons
    -0.45
    ječ
    -0.42
    npos
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.75
    الحياه
    0.75
    rungsseite
    0.71
    @[+][
    0.66
    saraba
    0.65
    protoimpl
    0.65
     محفوظة
    0.63
     disambiguazione
    0.60
    IsMutable
    0.60
    Obrázky
    0.59
    Activations Density 0.001%

    No Known Activations