© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91247
    Prev
    Next
    INDEX
    Explanations

    turn

    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
     usually
    -0.51
     generally
    -0.50
     rarely
    -0.49
     often
    -0.49
     probably
    -0.48
     are
    -0.47
     make
    -0.47
     typically
    -0.46
     work
    -0.46
     must
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.73
     frågan
    0.70
    ))));
    0.69
     particulières
    0.68
     berätt
    0.68
    '";
    0.68
    ')));
    0.67
    )))));
    0.65
    )))
    
    0.64
    ')";
    0.64
    Activations Density 0.003%

    No Known Activations