© 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. 0-CLT-HP
    7. 42194
    Prev
    Next
    INDEX
    Explanations

    platforms

    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
     platform
    -3.05
    platform
    -2.80
     Platform
    -2.80
    Platform
    -2.67
     platforms
    -2.56
     PLATFORM
    -2.48
     Platforms
    -2.41
     plataforma
    -2.31
     plateforme
    -2.17
    平台
    -2.11
    POSITIVE LOGITS
    ing
    0.54
    ingar
    0.50
     toque
    0.46
     wł
    0.44
    sentinel
    0.44
     AssemblyVersion
    0.43
    ("}");
    0.42
    arity
    0.42
    "}"
    0.42
    Coordonnées
    0.41
    Activations Density 0.275%

    No Known Activations