© 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. 5878
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
     operativos
    -0.43
    ža
    -0.43
     Deleting
    -0.42
    protocols
    -0.41
     certo
    -0.41
    thique
    -0.40
     ácidos
    -0.39
    Dealing
    -0.39
     perbaikan
    -0.39
     stie
    -0.38
    POSITIVE LOGITS
    Попис
    0.91
     ویکی‌پدی
    0.64
    ̍t
    0.64
     tartalomajánló
    0.63
    RenderAtEndOf
    0.61
     noDo
    0.61
     Walkover
    0.60
    цезда
    0.59
    idon
    0.57
    wyl
    0.57
    Activations Density 0.002%

    No Known Activations