© 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. 94548
    Prev
    Next
    INDEX
    Explanations

    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
     AppCompat
    -0.60
     vedea
    -0.59
    LogFactory
    -0.54
    CELLANEOUS
    -0.52
     déchir
    -0.52
     préc
    -0.48
     décid
    -0.48
     Blak
    -0.48
     étrang
    -0.47
     définiti
    -0.47
    POSITIVE LOGITS
     intern
    0.82
    AddTagHelper
    0.82
    KURZBESCHREIBUNG
    0.67
     Intern
    0.66
    ConstraintMaker
    0.65
    #+#
    0.63
    Intern
    0.63
     extern
    0.59
    WireFormatLite
    0.57
     <<<<<<<<<<<<<<
    0.57
    Activations Density 0.003%

    No Known Activations