© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1342
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    mybatisplus
    -0.57
    iastical
    -0.39
    cemic
    -0.37
    zzar
    -0.37
    lma
    -0.37
    ודם
    -0.35
    XmlAccessType
    -0.35
    AttributedString
    -0.35
    mpe
    -0.34
    LANTA
    -0.34
    POSITIVE LOGITS
    Lähteet
    0.88
    GEBURTSDATUM
    0.86
    Przypisy
    0.81
    Референце
    0.76
    مراجع
    0.75
    Hentet
    0.70
     ſmall
    0.68
    المراجع
    0.66
     protoimpl
    0.65
     发表于
    0.65
    Activations Density 0.006%

    No Known Activations