© 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. 41961
    Prev
    Next
    INDEX
    Explanations

    contractions ending in "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
     don
    -0.85
     isn
    -0.82
     doesn
    -0.80
     aren
    -0.77
     wasn
    -0.71
     haven
    -0.69
     didn
    -0.67
     wouldn
    -0.66
     Don
    -0.62
     hasn
    -0.61
    POSITIVE LOGITS
    '
    1.05
    AndEndTag
    0.75
    ValueStyle
    0.73
    \'
    0.71
    psack
    0.69
     @"/
    0.68
    ’
    0.68
     Monfieur
    0.68
    ChildScrollView
    0.67
    RegistryLite
    0.66
    Activations Density 0.088%

    No Known Activations