© 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. 20-CLT-HP
    7. 76798
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act-logits · 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
     externi
    -0.48
    Breadcrumb
    -0.39
     budete
    -0.35
     serez
    -0.35
    ăți
    -0.35
    antMatchers
    -0.34
    setopt
    -0.33
    You
    -0.33
    lasma
    -0.33
     avez
    -0.33
    POSITIVE LOGITS
     the
    1.01
     their
    1.01
     its
    0.98
     them
    0.92
     everything
    0.87
     his
    0.86
     an
    0.84
     itself
    0.84
     those
    0.82
     something
    0.82
    Activations Density 0.033%

    No Known Activations