© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 275
    Prev
    Next
    INDEX
    Explanations

    elements of complex mathematical expressions and notations

    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
    Архівовано
    -0.57
     auto
    -0.51
     Auto
    -0.51
     mé
    -0.49
    lico
    -0.49
    insatz
    -0.47
    ”:
    -0.47
    chale
    -0.46
    aven
    -0.45
     First
    -0.45
    POSITIVE LOGITS
     auroit
    0.73
    LookAnd
    0.71
    IContainer
    0.71
     Roskov
    0.70
     rêves
    0.69
     Wikimedijinoj
    0.68
     Италијани
    0.68
     Monfieur
    0.67
     feroit
    0.65
    aarrggbb
    0.65
    Activations Density 2.489%

    No Known Activations