© 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. 12-RES-MATRYOSHKA-DC
    7. 14039
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating potentiality or capability

    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
    ]}$
    -0.64
     form
    -0.63
    es
    -0.60
    ihe
    -0.58
    )}$
    -0.57
    adox
    -0.57
    حياتها
    -0.57
    ))}
    -0.56
     Vance
    -0.56
    nantes
    -0.56
    POSITIVE LOGITS
    CloseOperation
    0.82
     myſelf
    0.79
     Sarm
    0.76
     Shakspeare
    0.75
     متعلقه
    0.75
     chopsticks
    0.75
    expandindo
    0.74
     Wern
    0.73
     doInBackground
    0.73
     saturn
    0.72
    Activations Density 0.013%

    No Known Activations