© 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. 24-RES-MATRYOSHKA-DC
    7. 860
    Prev
    Next
    INDEX
    Explanations

    words pertaining to religion

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mom
    -0.76
     Euch
    -0.73
     Dad
    -0.59
     Python
    -0.59
     Вам
    -0.57
     Gennaio
    -0.57
     Deiner
    -0.54
     Вас
    -0.53
     Mommy
    -0.53
     Amazon
    -0.51
    POSITIVE LOGITS
     i
    0.95
     america
    0.78
     ive
    0.69
     theyre
    0.66
     japanese
    0.63
     москве
    0.63
     american
    0.62
     russia
    0.61
     ii
    0.60
     thursday
    0.60
    Activations Density 1.333%

    No Known Activations