© 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. 16324
    Prev
    Next
    INDEX
    Explanations

    references to specific movies, characters, and personal experiences in a conversational 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
    twimg
    -0.80
    انيف
    -0.77
    RTLD
    -0.71
    msgTypes
    -0.70
    matchCondition
    -0.69
    dafx
    -0.69
    PYX
    -0.67
    ScopeManager
    -0.66
    Personensuche
    -0.65
    ."],
    -0.65
    POSITIVE LOGITS
    hauser
    0.46
    parametrize
    0.46
     createState
    0.44
    makeText
    0.43
     CreateTagHelper
    0.43
     comentário
    0.42
    くら
    0.40
     GenerationType
    0.40
    FQ
    0.40
     jadx
    0.39
    Activations Density 0.018%

    No Known Activations