© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 555
    Prev
    Next
    INDEX
    Explanations

    the word "General," sometimes accompanied by "Electric."

    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.22.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.22.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
     للمعارف
    -0.68
    󠁿
    -0.66
     original
    -0.61
     aught
    -0.61
     originalmente
    -0.58
     myſelf
    -0.57
    EndContext
    -0.57
    pendenti
    -0.56
     Original
    -0.56
     VIDEOTAPE
    -0.56
    POSITIVE LOGITS
    purpose
    0.91
     purpose
    0.90
    issimo
    0.74
    GENERAL
    0.73
     Purpose
    0.71
    Purpose
    0.71
     relativity
    0.69
    isations
    0.68
    eneral
    0.68
     accepted
    0.67
    Activations Density 0.266%

    No Known Activations