© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3006
    Prev
    Next
    INDEX
    Explanations

    the word "total" and words associated with tallies and calculations

    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
     full
    -0.66
     Full
    -0.58
    Full
    -0.57
    ">—
    -0.54
    "{\
    -0.54
     FULL
    -0.53
    ccb
    -0.52
     complètes
    -0.52
    full
    -0.51
    igshid
    -0.50
    POSITIVE LOGITS
    itarianism
    0.84
    izator
    0.78
     noDo
    0.77
    Ener
    0.76
    expandindo
    0.70
     CreateTagHelper
    0.67
    izers
    0.67
    itarian
    0.66
    izing
    0.66
    exitRule
    0.66
    Activations Density 0.036%

    No Known Activations