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. 18499
    Prev
    Next
    INDEX
    Explanations

    section headings or structural markers in the text

    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
     phosphoric
    -0.65
     Oates
    -0.58
    uerre
    -0.57
    tvguidetime
    -0.57
    TargetException
    -0.55
    MemoryWarning
    -0.54
    meyi
    -0.54
    xaml
    -0.52
    WEBPACK
    -0.52
    ตำ
    -0.51
    POSITIVE LOGITS
     affich
    0.63
    jména
    0.63
     HttpNotFound
    0.61
     jScrollPane
    0.60
     avoient
    0.60
     Administrativna
    0.60
     Seeder
    0.58
     zelve
    0.56
    agisse
    0.55
     vettor
    0.54
    Activations Density 0.017%

    No Known Activations