© 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. 30979
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or claims

    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
     OnInit
    -0.68
    "]]
    -0.65
     Witkin
    -0.59
    AutoField
    -0.58
    ⓧ
    -0.58
     ActivatedRoute
    -0.58
    \}\\
    -0.57
    ChildScrollView
    -0.56
    ']>
    -0.54
    styleUrls
    -0.54
    POSITIVE LOGITS
     indeed
    0.77
     таки
    0.75
    确实
    0.68
    的确
    0.67
    确实是
    0.64
     כן
    0.64
    #
    0.64
    確實
    0.63
     inderdaad
    0.62
    erdings
    0.60
    Activations Density 0.153%

    No Known Activations