© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    the word "very"

    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
    setVerticalGroup
    -0.85
     betweenstory
    -0.73
    waitKey
    -0.70
     esternos
    -0.66
    تفصیلات
    -0.66
     onCancelled
    -0.65
    StructEnd
    -0.65
    AnchorStyles
    -0.65
     sepenuhnya
    -0.64
    @[+][
    -0.63
    POSITIVE LOGITS
    VERY
    0.67
     Very
    0.67
    Very
    0.65
     VERY
    0.65
    very
    0.62
     very
    0.55
    じゃない
    0.54
    thing
    0.53
    occasion
    0.50
     existence
    0.48
    Activations Density 0.071%

    No Known Activations