© 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. 0-CLT-HP
    7. 94552
    Prev
    Next
    INDEX
    Explanations

    publications, code

    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
     publication
    -1.23
    publication
    -0.90
     Go
    -0.85
     Publication
    -0.82
     follow
    -0.74
     "
    -0.68
     PUBLICATION
    -0.66
     
    -0.64
     “
    -0.62
     convention
    -0.61
    POSITIVE LOGITS
     purpoſe
    1.28
     myſelf
    1.25
     ſche
    1.13
     houſe
    1.13
     Monfieur
    1.13
     ſta
    1.13
     auroit
    1.13
     étoient
    1.12
     Efq
    1.12
     pleaſure
    1.12
    Activations Density 0.664%

    No Known Activations