© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74853
    Prev
    Next
    INDEX
    Explanations

    months or women

    np_max-act-logits · 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
    XmlAccessType
    -0.68
     disambiguazione
    -0.66
    rungsseite
    -0.66
    findpost
    -0.63
    TagHelpers
    -0.60
     виправивши
    -0.59
    Aiheesta
    -0.58
    Kaynakça
    -0.58
    adaptiveStyles
    -0.58
    vdash
    -0.57
    POSITIVE LOGITS
     women
    0.60
     month
    0.54
     monthly
    0.52
     mens
    0.51
     girls
    0.50
     months
    0.50
    Pap
    0.50
    Monthly
    0.49
    uebe
    0.49
     měsí
    0.49
    Activations Density 0.001%

    No Known Activations