© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95082
    Prev
    Next
    INDEX
    Explanations

    that

    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
     that
    -1.96
    that
    -1.50
     bahwa
    -1.17
     rằng
    -1.16
     kwamba
    -1.08
    That
    -1.05
     bahawa
    -0.99
    THAT
    -0.94
     ότι
    -0.93
     vérit
    -0.92
    POSITIVE LOGITS
     is
    0.91
     has
    0.76
     was
    0.76
     comes
    0.72
     corresponds
    0.72
     extends
    0.69
     goes
    0.68
     includes
    0.66
     they
    0.66
     occurs
    0.66
    Activations Density 0.463%

    No Known Activations