© 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. 22-RES-MATRYOSHKA-DC
    7. 1668
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to causation and reasoning

    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
    MessageOf
    -0.76
    tagHelperRunner
    -0.68
    ệc
    -0.62
     الحره
    -0.55
    IsContent
    -0.54
    érience
    -0.54
    sätzlich
    -0.53
     Италијани
    -0.51
    exitRule
    -0.51
    XmlAccessType
    -0.51
    POSITIVE LOGITS
     reasons
    2.58
     reason
    2.47
     cause
    2.22
    reasons
    2.20
     Reasons
    2.13
     why
    2.09
     causes
    2.09
    reason
    2.06
    Reasons
    2.06
    cause
    2.00
    Activations Density 1.832%

    No Known Activations