© 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. 0-CLT-HP
    7. 92368
    Prev
    Next
    INDEX
    Explanations

    steroids

    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
     commence
    -0.65
     Trevor
    -0.61
    Trevor
    -0.52
    utations
    -0.51
    Referências
    -0.44
     }}$}
    -0.43
    Nyt
    -0.42
    BRE
    -0.42
    gpu
    -0.41
    steroid
    -0.41
    POSITIVE LOGITS
    Portály
    0.73
     дописавши
    0.72
    QMetaType
    0.67
     stället
    0.65
    MigrationBuilder
    0.63
     CiNii
    0.62
     kasarigan
    0.61
     Hage
    0.60
    IndentedString
    0.60
    elemField
    0.60
    Activations Density 1.566%

    No Known Activations