© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41360
    Prev
    Next
    INDEX
    Explanations

    vitro

    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
    ########.
    -0.87
    ngdoc
    -0.82
     lenker
    -0.82
    NameInMap
    -0.81
    PerformLayout
    -0.80
     defStyleAttr
    -0.80
     resourceCulture
    -0.79
    FunctionFlags
    -0.79
     autorytatywna
    -0.77
     OFDb
    -0.77
    POSITIVE LOGITS
     terbuka
    0.45
    ia
    0.44
     ngayon
    0.41
     abiertos
    0.40
     Schä
    0.39
     impossibile
    0.39
     město
    0.39
     advocated
    0.39
     tässä
    0.39
     arasında
    0.38
    Activations Density 0.096%

    No Known Activations