© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    specific keywords or phrases related to calls or openings in a context, likely signifying transitions or highlights in a discussion or narrative

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    TagMode
    -0.81
     @"/
    -0.70
    ContextHolder
    -0.69
    новништво
    -0.67
     typelib
    -0.58
    ScopeManager
    -0.57
     DriverManager
    -0.56
    jectures
    -0.56
    SequentialGroup
    -0.56
    addPreferredGap
    -0.55
    POSITIVE LOGITS
    Bronnen
    0.59
     Puritans
    0.56
     Paralymp
    0.46
     overheard
    0.46
    CPtr
    0.46
     Caes
    0.45
    Erreferentziak
    0.44
    ніципалі
    0.44
     Gees
    0.44
     nór
    0.44
    Activations Density 0.000%

    No Known Activations