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. 15433
    Prev
    Next
    INDEX
    Explanations

    numerical values related to scientific measurements and experimental conditions

    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
     cut
    -0.52
     sp
    -0.52
    혁
    -0.45
    ur
    -0.44
    zte
    -0.43
    sp
    -0.42
     Tr
    -0.42
     complete
    -0.42
    COLUMN
    -0.42
    uttu
    -0.42
    POSITIVE LOGITS
    IContainer
    0.90
    PreferredItem
    0.81
     ویکی‌پدیای
    0.80
     leaſt
    0.75
     ModelExpression
    0.74
     poffible
    0.74
    ſelf
    0.73
    RTDA
    0.72
     wikipagina
    0.71
    ContentAsync
    0.71
    Activations Density 0.009%

    No Known Activations