© 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. 0-CLT-HP
    7. 42053
    Prev
    Next
    INDEX
    Explanations

    contractions using "n't"

    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
     wouldn
    -1.56
    wouldn
    -1.41
     Wouldn
    -1.36
     shouldn
    -1.24
     wouldnt
    -1.08
     Shouldn
    -1.08
    Wouldn
    -1.07
     wasn
    -0.87
     weren
    -0.85
     shouldnt
    -0.85
    POSITIVE LOGITS
    '
    0.87
    ’
    0.69
    \'
    0.65
    ʼ
    0.65
    ′
    0.63
    ʻ
    0.63
    ''
    0.57
    AndEndTag
    0.56
    `
    0.56
    ´
    0.56
    Activations Density 0.024%

    No Known Activations