© 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. 9143
    Prev
    Next
    INDEX
    Explanations

    variations of the word "manner" that describe how actions are performed

    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
    Negative Logits
    }))
    -1.01
    })));
    -0.96
    )))));
    -0.91
     HUGH
    -0.91
     Tuf
    -0.87
     Hughes
    -0.86
     Rufus
    -0.85
    ='')
    -0.84
    cheme
    -0.83
     ''}
    -0.83
    POSITIVE LOGITS
     Manner
    1.15
    er
    1.06
     manner
    1.00
    manner
    0.87
     manners
    0.80
     Manners
    0.73
     Mn
    0.65
     Angele
    0.65
     indietro
    0.64
    PMailer
    0.63
    Activations Density 0.005%

    No Known Activations