© 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. 1-CLT-HP
    7. 13280
    Prev
    Next
    INDEX
    Explanations

    debug

    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
     bug
    -1.55
     Bug
    -1.49
     bugs
    -1.42
    bug
    -1.42
    Bug
    -1.40
    bugs
    -1.40
     Bugs
    -1.19
    Bugs
    -1.17
     BUG
    -1.16
    BUG
    -1.11
    POSITIVE LOGITS
     AssemblyCulture
    0.63
    ging
    0.52
    wixt
    0.51
    View
    0.49
    gered
    0.48
    }()
    0.44
     vista
    0.44
     зрения
    0.43
    į
    0.42
    ged
    0.42
    Activations Density 0.013%

    No Known Activations