© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97086
    Prev
    Next
    INDEX
    Explanations

    giving examples

    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
     it
    -0.73
     we
    -0.72
     they
    -0.63
     you
    -0.63
     there
    -0.63
     if
    -0.57
     by
    -0.54
     through
    -0.51
    we
    -0.43
     to
    -0.42
    POSITIVE LOGITS
    nhung
    0.78
     '{@
    0.77
    GEBURTSDATUM
    0.76
    Portale
    0.71
    GEBURTS
    0.71
    Portail
    0.71
     BRARY
    0.71
    NUMX
    0.70
    esterday
    0.70
     betweenstory
    0.69
    Activations Density 0.010%

    No Known Activations