© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    adverbs and related descriptive words modifying verbs or entire clauses

    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
    principalColumn
    -0.87
    "])
    -0.84
    Tikang
    -0.83
    []
    -0.81
    httphttps
    -0.81
     <<<<<<<<<<<<<<
    -0.79
    ]--;
    -0.79
    EndInit
    -0.78
     AttributeSet
    -0.76
    TypedDataSet
    -0.72
    POSITIVE LOGITS
    &
    0.57
    .
    0.53
     &
    0.51
     be
    0.50
    ,
    0.50
     to
    0.50
     not
    0.49
     in
    0.49
     want
    0.48
    (
    0.48
    Activations Density 0.245%

    No Known Activations