© 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. 1531
    Prev
    Next
    INDEX
    Explanations

    the word "change" with contextual words around it

    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
     genomen
    -0.60
    
    -0.60
     достижения
    -0.54
    closedir
    -0.54
    सर
    -0.53
     sürd
    -0.50
    izzard
    -0.49
     blz
    -0.49
    égard
    -0.48
    osť
    -0.48
    POSITIVE LOGITS
     Change
    0.85
    แป
    0.84
     Changing
    0.84
    Changing
    0.82
    changing
    0.81
     Changed
    0.78
     Changes
    0.78
     direction
    0.77
     CHANGE
    0.77
     CHANG
    0.75
    Activations Density 0.386%

    No Known Activations