© 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. 94324
    Prev
    Next
    INDEX
    Explanations

    churches religion

    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
    GEBURTSDATUM
    -1.09
    AnchorStyles
    -0.98
     pleaſure
    -0.94
    +#+#
    -0.93
     تضيفلها
    -0.92
     BoxFit
    -0.92
    󠁴
    -0.92
     متعلقه
    -0.92
    IsMutable
    -0.92
    例句
    -0.91
    POSITIVE LOGITS
     of
    0.61
    .
    0.48
     best
    0.46
     past
    0.46
     fast
    0.46
     A
    0.45
    avro
    0.45
    ,
    0.44
     models
    0.42
     plans
    0.42
    Activations Density 0.083%

    No Known Activations