© 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. 97433
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
     they
    -0.56
     it
    -0.52
     a
    -0.52
     killing
    -0.52
    GeneratedValue
    -0.48
     the
    -0.47
     welcoming
    -0.45
     chipping
    -0.45
    essing
    -0.44
     gant
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.88
    +#+
    0.81
     betweenstory
    0.79
     Administrativna
    0.78
    +#+#
    0.77
    RefNanny
    0.77
    rungsseite
    0.74
     nahilalakip
    0.74
    ----</
    0.74
     can
    0.72
    Activations Density 0.003%

    No Known Activations