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. 211
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions related to exponential decay and probability distributions

    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
     CreateTagHelper
    -0.77
    Personensuche
    -0.73
    ########.
    -0.71
     AspNetCore
    -0.70
     متعلقه
    -0.68
     للمعارف
    -0.68
    IntoConstraints
    -0.68
    MigrationBuilder
    -0.64
    колеп
    -0.63
    </thead>
    -0.62
    POSITIVE LOGITS
     exp
    0.70
    exp
    0.66
     expon
    0.64
     Exponential
    0.59
     exponential
    0.59
    Exp
    0.54
     MaterialApp
    0.52
     log
    0.50
    exponential
    0.50
    Exponential
    0.50
    Activations Density 1.320%

    No Known Activations