© 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. 0-CLT-HP
    7. 43857
    Prev
    Next
    INDEX
    Explanations

    Scientific/research topics

    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
     Sutton
    -1.55
    Sutton
    -1.19
    Personendaten
    -0.81
    uronic
    -0.78
     resourceCulture
    -0.58
    دانشنامهٔ
    -0.58
    UTTON
    -0.57
    UnusedPrivate
    -0.50
    WireFormatLite
    -0.50
    EOR
    -0.50
    POSITIVE LOGITS
    
    0.76
    onViewCreated
    0.57
    tocin
    0.56
     BorderSide
    0.55
    gebnisse
    0.53
    wnia
    0.52
     Bernice
    0.51
    StructEnd
    0.50
    stahl
    0.50
    Banks
    0.50
    Activations Density 1.545%

    No Known Activations