© 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. 42143
    Prev
    Next
    INDEX
    Explanations

    mine

    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
    ,
    -0.84
    mine
    -0.82
     mine
    -0.76
     of
    -0.72
     (
    -0.69
    ’
    -0.69
    .
    -0.69
    '
    -0.67
    /
    -0.65
    :
    -0.60
    POSITIVE LOGITS
     itſelf
    1.84
     myſelf
    1.72
     Jefus
    1.66
    ſelves
    1.64
     themſelves
    1.60
     ſeveral
    1.57
     houſe
    1.53
    GEBURTSDATUM
    1.53
    ſelf
    1.52
     Monfieur
    1.52
    Activations Density 0.010%

    No Known Activations