© 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. 4-CLT-HP
    7. 4781
    Prev
    Next
    INDEX
    Explanations

    code snippets and documentation

    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
    uertos
    -1.03
    saraba
    -0.77
    UnusedPrivate
    -0.75
    GeoNames
    -0.69
    kloped
    -0.65
    IVEREF
    -0.61
     iNdEx
    -0.61
    entiary
    -0.59
    *)((
    -0.58
    Witam
    -0.57
    POSITIVE LOGITS
     kasarigan
    0.50
    Geplaatst
    0.49
    ChildScrollView
    0.46
    igshid
    0.43
    arım
    0.42
    ضي
    0.42
     esternos
    0.41
    lessness
    0.41
     Combs
    0.40
    iosk
    0.40
    Activations Density 0.001%

    No Known Activations