© 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. 5-CLT-HP
    7. 4421
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    
    -0.57
     CiNii
    -0.54
    ="&#
    -0.49
    >//
    -0.45
     Falk
    -0.45
    orit
    -0.44
     '-',
    -0.42
    پس
    -0.42
    bootstrapcdn
    -0.42
    ragan
    -0.42
    POSITIVE LOGITS
     geométrico
    0.77
    ScopeManager
    0.68
     виправивши
    0.67
    harapkan
    0.63
    AutoSize
    0.63
    ClientSize
    0.62
    Tembelea
    0.62
    LEncoder
    0.61
     puissiez
    0.59
     linkovi
    0.59
    Activations Density 0.001%

    No Known Activations