© 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. 1-CLT-HP
    7. 46170
    Prev
    Next
    INDEX
    Explanations

    inspiring

    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
    género
    -0.52
    enumi
    -0.52
    bootstrapcdn
    -0.50
    ">—
    -0.48
    PreInfinity
    -0.48
    ppus
    -0.48
    utup
    -0.48
     NSCoder
    -0.47
    rätt
    -0.45
    richting
    -0.45
    POSITIVE LOGITS
    ManagedBean
    0.66
    locene
    0.56
    MIDDLEWARE
    0.54
     Sarg
    0.54
    Personensuche
    0.54
     الحره
    0.53
    windowFixed
    0.53
    ʖ
    0.52
    UnknownFields
    0.52
     pylab
    0.52
    Activations Density 0.162%

    No Known Activations