© 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. 5-CLT-HP
    7. 96788
    Prev
    Next
    INDEX
    Explanations

    years/numbers

    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
     définiti
    -0.57
    MethodManager
    -0.56
     gethan
    -0.55
    衅
    -0.55
    ंदीखरीदारी
    -0.55
     turísticos
    -0.54
     semula
    -0.54
     törvény
    -0.54
     surla
    -0.53
    JspWriter
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.49
     bulunabilir
    0.43
    .[/
    0.43
    ]-'
    0.40
    CORBA
    0.40
     ***!
    0.40
     للمعارف
    0.39
    nich
    0.38
    Beds
    0.38
    }^{-}$
    0.38
    Activations Density 0.126%

    No Known Activations