© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71648
    Prev
    Next
    INDEX
    Explanations

    nighttime

    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
     Bigelow
    -0.60
    BufferException
    -0.58
    onActivityResult
    -0.58
    évaluateur
    -0.58
    WriteBarrier
    -0.57
    complexContent
    -0.56
    FieldBuilder
    -0.54
    wezen
    -0.53
    ++];
    -0.53
    ilhas
    -0.52
    POSITIVE LOGITS
     late
    0.75
     night
    0.71
     nighttime
    0.70
     Late
    0.61
     midnight
    0.60
     nights
    0.59
    Late
    0.58
    late
    0.57
     evening
    0.56
     NIGHT
    0.54
    Activations Density 0.000%

    No Known Activations