© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 470
    Prev
    Next
    INDEX
    Explanations

    rand

    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
     Sociales
    -0.52
     devriez
    -0.43
    BuildContext
    -0.40
    ksiä
    -0.40
    The
    -0.39
    //*[@
    -0.38
    mua
    -0.38
     antigua
    -0.38
    mtb
    -0.37
    UpInside
    -0.37
    POSITIVE LOGITS
    Personendaten
    1.00
    tvguidetime
    0.95
     EconPapers
    0.84
     Paglinawan
    0.77
    MigrationBuilder
    0.74
     continúas
    0.73
     Вікіпе
    0.71
    期刊论文
    0.71
    ophor
    0.67
    Попис
    0.66
    Activations Density 0.008%

    No Known Activations