© 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. 12-RES-MATRYOSHKA-DC
    7. 11565
    Prev
    Next
    INDEX
    Explanations

    the word "stick" and its variations in different contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    ValueStyle
    -1.13
    tinyos
    -1.00
     Biôgrafia
    -0.91
    zeß
    -0.89
    bellum
    -0.84
    τουργ
    -0.83
    setFirstName
    -0.82
    InSection
    -0.81
    __*/
    -0.80
     Champlain
    -0.80
    POSITIVE LOGITS
     stick
    1.63
     Stick
    1.44
     sticks
    1.43
     STICK
    1.41
    Stick
    1.37
    stick
    1.36
     Sticks
    1.34
     stuck
    1.30
     sticking
    1.28
    STICK
    1.27
    Activations Density 0.010%

    No Known Activations