© 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. 30341
    Prev
    Next
    INDEX
    Explanations

    the word "Interestingly" and similar expressions that introduce noteworthy information

    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
     voeten
    -0.57
    us
    -0.55
     tranquillo
    -0.54
    u
    -0.53
     ș
    -0.50
     sogget
    -0.50
     înc
    -0.50
     nomme
    -0.50
     table
    -0.49
    <bos>
    -0.49
    POSITIVE LOGITS
     Efq
    0.68
    ])+
    0.64
     Sigism
    0.64
    ]));
    0.63
    quartered
    0.62
    zzarella
    0.62
    )");
    0.62
    ])]
    0.61
     rootReducer
    0.61
    ########.
    0.61
    Activations Density 0.007%

    No Known Activations