© 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. 1347
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "has" or "have" alongside words that indicate significance, breadth, or impacts

    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
    ThroughAttribute
    -0.66
     defaultstate
    -0.65
    setVerticalGroup
    -0.63
    fromnode
    -0.63
    posables
    -0.61
    EndInit
    -0.60
    IsContent
    -0.59
    []
    -0.59
    HasForeignKey
    -0.58
    forChild
    -0.58
    POSITIVE LOGITS
     implications
    1.03
     significance
    1.03
     meaning
    0.94
     relevance
    0.92
     impact
    0.92
     Significance
    0.89
     ramifications
    0.88
     Implications
    0.85
     value
    0.82
     effect
    0.79
    Activations Density 0.753%

    No Known Activations