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. 32172
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to engineering and scientific processes

    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
     poveznice
    -0.75
    AnchorStyles
    -0.70
     createState
    -0.68
     ویکی‌پدیا
    -0.68
     gynhyrchwyd
    -0.67
    __":
    
    -0.66
     оригіналу
    -0.66
    ftagPool
    -0.65
     للمعارف
    -0.65
     Мексичка
    -0.64
    POSITIVE LOGITS
    .
    0.70
     Viability
    0.53
    enschap
    0.52
    comparable
    0.49
    legende
    0.48
     diffusivity
    0.47
    CastException
    0.47
     tymp
    0.47
     nodules
    0.46
     decorativos
    0.46
    Activations Density 0.607%

    No Known Activations