© 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. 5-CLT-HP
    7. 92749
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
    astia
    -1.92
    saraba
    -0.59
     незавершена
    -0.57
    istoitu
    -0.57
    发表于
    -0.56
     useRouter
    -0.55
     Ause
    -0.52
    ::_('
    -0.52
    vaders
    -0.51
     incin
    -0.51
    POSITIVE LOGITS
    cyjne
    0.52
    لينكات
    0.49
    FormTagHelper
    0.47
     personalidade
    0.44
    cyjna
    0.44
     riesgo
    0.44
     TextAppearance
    0.43
     prochains
    0.43
    ///</
    0.43
    новниш
    0.43
    Activations Density 0.001%

    No Known Activations