© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42554
    Prev
    Next
    INDEX
    Explanations

    Christianity

    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
     itſelf
    -0.88
    <bos>
    -0.84
    oneofs
    -0.81
     uncin
    -0.81
    يكب
    -0.80
     myſelf
    -0.77
     beginnetje
    -0.76
     fusca
    -0.73
     ACI
    -0.72
     سكانية
    -0.72
    POSITIVE LOGITS
    SequentialGroup
    0.46
    Atsauces
    0.45
     Anyway
    0.41
     hombros
    0.40
    enaam
    0.40
    addPreferredGap
    0.39
     piede
    0.38
     felizes
    0.38
    Anyway
    0.38
     extensively
    0.37
    Activations Density 0.064%

    No Known Activations