© 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. 1-CLT-HP
    7. 10219
    Prev
    Next
    INDEX
    Explanations

    segment

    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
    setVerticalGroup
    -0.92
    <?>>
    -0.69
    httphttps
    -0.68
     AssemblyCompany
    -0.68
    الدراسه
    -0.68
    ResumeLayout
    -0.65
     EnglishChoose
    -0.65
    Архівовано
    -0.64
    脚注の使い方
    -0.63
     мәкал
    -0.63
    POSITIVE LOGITS
    ագրություններ
    0.54
    󠁢
    0.45
    Kens
    0.43
    ittäin
    0.42
    ViewFeatures
    0.42
    ionalmente
    0.42
    žin
    0.42
     carrying
    0.41
    ITECH
    0.41
    fitriones
    0.41
    Activations Density 0.076%

    No Known Activations