© 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. 5788
    Prev
    Next
    INDEX
    Explanations

    ative

    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
    Personensuche
    -0.81
    __(/*!
    -0.65
    AsUp
    -0.64
    bootstrapcdn
    -0.62
    SharedDtor
    -0.61
    ulemon
    -0.60
    InjectAttribute
    -0.59
    )_/¯
    -0.59
    .},
    -0.59
    ieteur
    -0.59
    POSITIVE LOGITS
    Marne
    0.53
    RenderAtEndOf
    0.50
    protoimpl
    0.49
    Referencies
    0.47
     molecule
    0.46
    level
    0.45
    Архівовано
    0.45
     déplacements
    0.43
     or
    0.43
    Rhestr
    0.43
    Activations Density 0.006%

    No Known Activations