© 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. 0-CLT-HP
    7. 97119
    Prev
    Next
    INDEX
    Explanations

    Ph

    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
    fml
    -0.55
    sz
    -0.52
    ]--;
    -0.51
     Contemporary
    -0.49
    CEPTION
    -0.48
    dbach
    -0.47
    e
    -0.47
    amar
    -0.47
     dissolved
    -0.46
     admission
    -0.46
    POSITIVE LOGITS
     OFDb
    0.75
    PreferredItem
    0.74
     EconPapers
    0.73
    tagHelperRunner
    0.72
    rases
    0.65
     igång
    0.62
    Brainz
    0.59
    Демографія
    0.59
    IContainer
    0.57
    ArrowToggle
    0.57
    Activations Density 0.242%

    No Known Activations