© 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. 29776
    Prev
    Next
    INDEX
    Explanations

    statements indicating judgment or declarations regarding legal matters

    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
    tvguidetime
    -0.96
     propOrder
    -0.91
    DockStyle
    -0.86
     مرئيه
    -0.83
    SourceChecksum
    -0.82
    rungsseite
    -0.81
     الرياضيه
    -0.81
    TagMode
    -0.79
    uxxxx
    -0.77
    ReusableCell
    -0.76
    POSITIVE LOGITS
    我认为
    0.48
    我觉得
    0.45
    </h6>
    0.44
     shouldn
    0.44
     solchen
    0.43
    ுக்கு
    0.42
    這種
    0.41
    </em>
    0.41
     I
    0.40
     .
    0.40
    Activations Density 0.291%

    No Known Activations