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. 26470
    Prev
    Next
    INDEX
    Explanations

    periods and sentences that indicate completion or finality

    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
     ویکی‌پدیای
    -0.60
    <%=
    -0.59
     мәкалә
    -0.55
    Unnamed
    -0.54
     endforeach
    -0.54
     vorg
    -0.53
    ViewImports
    -0.53
     Polic
    -0.52
    éphane
    -0.51
     NDEBUG
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.63
    
    0.59
    +#+
    0.59
    Cyfarwyddwr
    0.57
    ########.
    0.57
    ELTS
    0.56
     gyhoeddwyd
    0.56
     similaires
    0.55
     suivante
    0.53
    hoeddwyd
    0.53
    Activations Density 0.009%

    No Known Activations