© 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. 4-CLT-HP
    7. 169
    Prev
    Next
    INDEX
    Explanations

    through/across

    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
     felices
    -0.56
    tvguidetime
    -0.56
     igång
    -0.50
     minhas
    -0.50
     känna
    -0.49
     estrena
    -0.49
     hemsida
    -0.48
     vänner
    -0.48
     gustan
    -0.47
     nele
    -0.47
    POSITIVE LOGITS
     time
    0.88
     some
    0.71
    ArrowToggle
    0.70
     selected
    0.66
     springfox
    0.65
     فريبيس
    0.62
    proken
    0.60
     parts
    0.59
     town
    0.59
     centuries
    0.58
    Activations Density 0.003%

    No Known Activations