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. 12165
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and concepts related to stochastic 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
     viewType
    -0.55
    ürzt
    -0.47
     gouver
    -0.46
    Ket
    -0.45
    zsef
    -0.44
     Attack
    -0.43
    Foreground
    -0.43
    Mixin
    -0.43
     Sobre
    -0.43
     trous
    -0.42
    POSITIVE LOGITS
    `{.
    0.84
     SwitchCompat
    0.80
    Identyfik
    0.79
    ']")
    0.77
    ніципалі
    0.75
     OFDb
    0.75
    HtmlAttribute
    0.75
    ']").
    0.74
    ActionCreators
    0.73
    AddTagHelper
    0.71
    Activations Density 0.076%

    No Known Activations