© 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. 96475
    Prev
    Next
    INDEX
    Explanations

    basketball and handball

    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
    </h2>
    -0.39
    řen
    -0.38
     stra
    -0.38
     Diakses
    -0.38
    ások
    -0.37
    жба
    -0.37
     Socialista
    -0.37
    ri
    -0.37
     г
    -0.35
     vůbec
    -0.35
    POSITIVE LOGITS
     HasFactory
    0.86
    MemoryWarning
    0.81
     ProtoMessage
    0.80
     FetchType
    0.74
    AsUp
    0.72
    UAWEI
    0.72
     NSCoder
    0.72
    الحياه
    0.72
    édrale
    0.68
     disambiguazione
    0.68
    Activations Density 0.022%

    No Known Activations