© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    light

    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
    findpost
    -0.91
    bootstrapcdn
    -0.88
    клопе
    -0.87
    GEBURTSDATUM
    -0.87
    новништво
    -0.86
    存于互联网档案馆
    -0.84
    ViewFeatures
    -0.83
    Hauptartikel
    -0.80
    Tikang
    -0.78
    ContentAsync
    -0.75
    POSITIVE LOGITS
     CascadeType
    0.44
     are
    0.43
     is
    0.40
    Passing
    0.40
     will
    0.40
     cannot
    0.38
     passaggio
    0.38
     passage
    0.36
    ряда
    0.35
     Vorgang
    0.35
    Activations Density 0.009%

    No Known Activations