© 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. 94589
    Prev
    Next
    INDEX
    Explanations

    to

    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
    BagLayout
    -0.64
    BagConstraints
    -0.63
    BufferException
    -0.63
    StoryboardSegue
    -0.62
     Administrativna
    -0.61
     Wiktionnaire
    -0.61
    Démographie
    -0.60
    annica
    -0.59
     geldt
    -0.56
    hadores
    -0.54
    POSITIVE LOGITS
     the
    0.53
    ting
    0.50
     something
    0.50
    น
    0.49
    n
    0.49
     get
    0.45
     achieve
    0.45
    ogast
    0.45
    st
    0.45
    l
    0.44
    Activations Density 0.069%

    No Known Activations