© 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. 0-CLT-HP
    7. 95556
    Prev
    Next
    INDEX
    Explanations

    Railroad related texts

    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
    Negative Logits
     Railroad
    -0.65
     railroad
    -0.57
     RAILROAD
    -0.55
    STONE
    -0.54
     virus
    -0.54
     rumor
    -0.54
    م
    -0.50
    thunk
    -0.50
    Rail
    -0.48
    loir
    -0.48
    POSITIVE LOGITS
    ing
    0.80
     ſche
    0.75
     Anſ
    0.74
     Efq
    0.71
     houſe
    0.71
    er
    0.70
    es
    0.69
     Majefty
    0.69
    Chham
    0.67
     purpoſe
    0.67
    Activations Density 0.250%

    No Known Activations