© 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. 20-CLT-HP
    7. 72478
    Prev
    Next
    INDEX
    Explanations

    academic/technical text

    np_max-act-logits · 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
     ivelany
    -0.75
    FTFY
    -0.73
    IntoConstraints
    -0.73
    MetaObject
    -0.67
     Uniti
    -0.66
    HasForeignKey
    -0.66
    ounid
    -0.66
    -------------</
    -0.66
    gonic
    -0.65
    ❋
    -0.65
    POSITIVE LOGITS
     spy
    0.45
     perang
    0.40
     iprot
    0.38
     glass
    0.37
     Spies
    0.36
     opera
    0.36
     παρα
    0.34
     believing
    0.34
    are
    0.33
    asso
    0.33
    Activations Density 0.001%

    No Known Activations