© 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. 0-CLT-HP
    4. 1898
    Prev
    Next
    INDEX
    Explanations

    seems

    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
    ()]);
    -0.67
     Efq
    -0.65
    "]];
    -0.63
    >');
    -0.61
    TypedDataSet
    -0.61
     Theſe
    -0.61
    "])
    
    -0.60
    >';
    
    -0.59
    IsContent
    -0.57
    "]);
    
    -0.57
    POSITIVE LOGITS
     propOrder
    0.68
     the
    0.68
     always
    0.67
     to
    0.66
     both
    0.66
     just
    0.64
     not
    0.63
     consultato
    0.62
     that
    0.60
     immediately
    0.60
    Activations Density 0.133%

    No Known Activations