© 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. 38371
    Prev
    Next
    INDEX
    Explanations

    positional

    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
    i
    -0.74
    s
    -0.74
    e
    -0.72
    ly
    -0.68
    ed
    -0.64
    a
    -0.64
    l
    -0.64
    d
    -0.64
    t
    -0.63
    ry
    -0.61
    POSITIVE LOGITS
    UnusedPrivate
    0.73
    IsMutable
    0.70
    OrNil
    0.65
     typelib
    0.63
    nodoc
    0.61
     NavController
    0.59
     onCreateView
    0.59
    ecma
    0.58
    RefNanny
    0.57
    TagMode
    0.57
    Activations Density 0.314%

    No Known Activations