© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    the word "right" and "back"

    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
    tagHelperRunner
    -1.02
    AsUp
    -0.87
    IndentedString
    -0.82
    UnusedPrivate
    -0.82
     NSCoder
    -0.81
    ⓧ
    -0.77
    +#+#
    -0.76
     الحره
    -0.76
    aarrggbb
    -0.76
    expandindo
    -0.75
    POSITIVE LOGITS
     now
    1.11
    now
    0.84
     ahora
    0.80
     NOW
    0.74
     wrongs
    0.72
     Now
    0.68
     away
    0.63
    Now
    0.63
     maintenant
    0.63
    NOW
    0.62
    Activations Density 0.069%

    No Known Activations