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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19949
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "any" in various contexts within legal or regulatory discussions

    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
    ^(@)
    -0.82
     createContext
    -0.81
     ―――――
    -0.77
     resourceCulture
    -0.74
     Anſ
    -0.72
     Houſe
    -0.72
     doubtnut
    -0.69
     BIBSYS
    -0.69
     Diſ
    -0.67
     raiſ
    -0.67
    POSITIVE LOGITS
     للمعارف
    0.61
    enschaft
    0.58
    XmlAccessorType
    0.55
     
    0.54
    cepteur
    0.52
     $
    0.51
    nologies
    0.51
    urence
    0.47
    Pyx
    0.47
    ressible
    0.47
    Activations Density 0.013%

    No Known Activations