© 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. 4914
    Prev
    Next
    INDEX
    Explanations

    know

    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
    featureID
    -0.73
    tagHelperRunner
    -0.72
    +#+#
    -0.70
    PropertyChanging
    -0.69
     Administrativna
    -0.65
    NameInMap
    -0.65
    igshid
    -0.63
    oredCriteria
    -0.62
     myſelf
    -0.61
    OrBuilder
    -0.61
    POSITIVE LOGITS
    demon
    0.82
     demonstrating
    0.81
     demonstration
    0.73
     demonstrate
    0.72
     demonstrated
    0.71
     demo
    0.70
     demonstrates
    0.70
     Demonstr
    0.68
    Demon
    0.66
     Demonstrate
    0.65
    Activations Density 0.000%

    No Known Activations