Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 32298
    Prev
    Next
    INDEX
    Explanations

    terms related to "legacy," especially pertaining to cultural or historical significance

    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
    GTCX
    -0.81
     Nip
    -0.80
    IntoConstraints
    -0.80
    extAlignment
    -0.79
     
    -0.79
    GoogleApiClient
    -0.79
    moveToFirst
    -0.77
     antiqu
    -0.75
    RuleContext
    -0.75
     StringField
    -0.75
    POSITIVE LOGITS
     Legacy
    1.38
    Legacy
    1.27
     legacy
    1.15
    legacy
    1.02
     LEG
    0.95
     legacies
    0.93
    LEG
    0.80
    ACY
    0.75
     Leg
    0.74
    ritage
    0.74
    Activations Density 0.002%

    No Known Activations