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. 17580
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operations, particularly involving equations and logical principles

    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
    RegressionTest
    -0.52
    plum
    -0.47
     stiff
    -0.46
    клопе
    -0.46
    ーム
    -0.46
    Formats
    -0.45
     समीक्षाओं
    -0.45
    pertino
    -0.45
    Бележки
    -0.44
    Formato
    -0.44
    POSITIVE LOGITS
    ^(@)
    0.79
    archiviato
    0.67
     themſelves
    0.63
     myſelf
    0.60
     Jefus
    0.59
    IntoConstraints
    0.59
    ViewFeatures
    0.58
    jago
    0.58
     crossorigin
    0.58
     campagnes
    0.57
    Activations Density 0.229%

    No Known Activations