© 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. 5-CLT-HP
    7. 2729
    Prev
    Next
    INDEX
    Explanations

    -

    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
    OGND
    -1.08
     незавершена
    -0.98
    expandindo
    -0.96
     AssemblyCulture
    -0.94
    GEBURTSDATUM
    -0.93
     propOrder
    -0.87
    AndEndTag
    -0.86
     Roskov
    -0.86
    Autoritní
    -0.83
     NSCoder
    -0.83
    POSITIVE LOGITS
    ADES
    0.45
    =$?
    0.38
    ссор
    0.38
    .
    0.38
     proper
    0.36
    årige
    0.36
     izay
    0.35
    ades
    0.34
    }$.\\
    0.33
     necessidade
    0.32
    Activations Density 0.017%

    No Known Activations