© 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. 20-CLT-HP
    7. 76054
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    ConstraintMaker
    -0.84
    principalColumn
    -0.76
     also
    -0.73
     hObject
    -0.72
    KURZBESCHREIBUNG
    -0.71
    
    -0.70
    ResumeLayout
    -0.68
     незавершена
    -0.66
    Chham
    -0.66
    also
    -0.65
    POSITIVE LOGITS
     is
    1.34
     are
    1.30
     will
    1.12
     can
    1.00
     would
    0.92
     was
    0.91
     were
    0.85
     shall
    0.83
     may
    0.83
     should
    0.78
    Activations Density 0.001%

    No Known Activations