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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38926
    Prev
    Next
    INDEX
    Explanations

    projects

    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
     côtes
    -0.45
     největ
    -0.41
     accidentes
    -0.39
    ուն
    -0.37
     meccan
    -0.36
     famiglie
    -0.36
     tecnica
    -0.36
     zuverläs
    -0.36
     familles
    -0.35
    Fax
    -0.34
    POSITIVE LOGITS
    +#+#
    0.95
    makeConstraints
    0.87
    RenderAtEndOf
    0.83
    parsedMessage
    0.80
     Signalez
    0.78
     referenties
    0.76
     Effort
    0.75
    AsUp
    0.75
    ValueStyle
    0.74
     ujednoznacz
    0.74
    Activations Density 0.178%

    No Known Activations