© 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. 22-RES-MATRYOSHKA-DC
    7. 2931
    Prev
    Next
    INDEX
    Explanations

    words from a variety of categories, including: emotions, death, music, authority, location, measurement, harm, law, AI dialog, genetics, code styling.

    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
     wireType
    -0.91
    ]")]
    -0.84
    Παραπομπές
    -0.79
    ErrorListener
    -0.78
    Билгалдахарш
    -0.76
     noqa
    -0.76
    ]),
    -0.74
     createState
    -0.74
     חיצוניים
    -0.73
    writeFieldEnd
    -0.73
    POSITIVE LOGITS
     enfans
    0.66
     auroit
    0.56
     împreună
    0.54
     avoient
    0.53
     entrambi
    0.50
     étoit
    0.50
     détru
    0.49
     titolata
    0.48
    TagMode
    0.48
     étoient
    0.47
    Activations Density 2.249%

    No Known Activations