© 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. 1-CLT-HP
    7. 12439
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
     vuotta
    -0.60
     hason
    -0.57
    тифика
    -0.54
     väli
    -0.54
    NEGATIVE
    -0.53
     elä
    -0.52
     condam
    -0.52
     négatif
    -0.51
     lisäksi
    -0.51
     nélk
    -0.51
    POSITIVE LOGITS
    CppMethod
    0.94
    ArrowToggle
    0.74
    sidemargin
    0.64
    帖最后由
    0.62
    TemporalType
    0.61
     Villiers
    0.57
     Tract
    0.55
    MathML
    0.53
    Geplaatst
    0.53
    ölkerung
    0.53
    Activations Density 0.057%

    No Known Activations