© 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. 12-RES-MATRYOSHKA-DC
    7. 15482
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals in a news context

    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
    mybatisplus
    -0.52
    igsaw
    -0.48
    ]}>
    -0.48
     lots
    -0.45
    蹦
    -0.45
    Eloquent
    -0.44
     Lots
    -0.44
    GeoNames
    -0.44
    tramp
    -0.44
     Wikispecies
    -0.43
    POSITIVE LOGITS
    hyrchwyd
    0.84
    aarrggbb
    0.77
     oprot
    0.63
     pinulongan
    0.62
     nakalista
    0.61
    قایناقلار
    0.59
    FunctionFlags
    0.58
     resourceCulture
    0.58
    хьтан
    0.56
    XmlType
    0.56
    Activations Density 0.054%

    No Known Activations