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. 6321
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or monetary values

    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
     EconPapers
    -0.90
    apimachinery
    -0.85
    +#+#
    -0.81
    StoryboardSegue
    -0.76
    Geplaatst
    -0.75
     zvuky
    -0.73
     ModelExpression
    -0.73
     صوتيه
    -0.73
    enumii
    -0.71
    AndEndTag
    -0.70
    POSITIVE LOGITS
    Prima
    0.48
    utete
    0.47
    RootPath
    0.45
     Prima
    0.44
    corresponding
    0.44
    vák
    0.44
    intelligible
    0.44
    どうか
    0.43
    ILIA
    0.43
    ányi
    0.42
    Activations Density 0.437%

    No Known Activations