© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 252
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of making deductions or conclusions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     untuk
    -0.68
    for
    -0.68
     apud
    -0.63
    FailureListener
    -0.63
    MessageTagHelper
    -0.63
     для
    -0.59
    Of
    -0.58
    forKey
    -0.57
    FOR
    -0.57
    sebagai
    -0.57
    POSITIVE LOGITS
     primarily
    0.84
     estekak
    0.82
     chiefly
    0.77
     principally
    0.73
     mainly
    0.73
     solely
    0.72
     predominantly
    0.70
     Primarily
    0.68
    primarily
    0.67
     largely
    0.66
    Activations Density 2.758%

    No Known Activations