© 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. 1-CLT-HP
    7. 10472
    Prev
    Next
    INDEX
    Explanations

    Jewish religious figures/topics

    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
     مشين
    -0.65
     متعلقه
    -0.64
    moiselle
    -0.64
     Exactos
    -0.58
    Palmar
    -0.57
    DebuggerNonUser
    -0.57
    >--}}
    -0.57
    --}}
    -0.57
    ...');
    -0.56
     rabbi
    -0.56
    POSITIVE LOGITS
     trucks
    0.48
     preference
    0.48
     Lug
    0.47
     drivers
    0.46
     decline
    0.45
     vitt
    0.44
     Público
    0.44
    ftagPool
    0.44
    Ks
    0.44
    omitempty
    0.44
    Activations Density 0.070%

    No Known Activations