© 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. 974
    Prev
    Next
    INDEX
    Explanations

    contextual clues (words like "until", "after", "before", "therefore", "by", etc.) and punctuation that indicate a relationship between pieces of information being presented, and may also respond to sexually suggestive content

    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
     uovo
    -0.69
     feroit
    -0.67
     financeira
    -0.66
     étoient
    -0.66
     trasparente
    -0.65
     épaules
    -0.64
     bună
    -0.63
     avoient
    -0.63
     تضيفلها
    -0.63
     lèvres
    -0.62
    POSITIVE LOGITS
    HasAnnotation
    0.63
    клопе
    0.61
    RepeatedField
    0.54
    ArrowToggle
    0.54
    ropractic
    0.54
    исленность
    0.54
    derung
    0.51
    ɵɵelementStart
    0.49
    vantages
    0.49
    Telefax
    0.48
    Activations Density 3.002%

    No Known Activations