© 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. 28244
    Prev
    Next
    INDEX
    Explanations

    references to libraries or collections of code and resources

    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
    ab
    -0.70
    toEqual
    -0.68
    Ned
    -0.65
     SES
    -0.62
     ab
    -0.60
     cherchez
    -0.60
    پرس
    -0.59
    зумі
    -0.59
     fus
    -0.59
    lious
    -0.58
    POSITIVE LOGITS
    %)$
    1.00
    styleType
    0.98
     libraries
    0.91
     Libraries
    0.89
     ſche
    0.89
    ंदीखरीदारी
    0.84
     Culver
    0.84
    ']")
    0.84
    ſelf
    0.83
    library
    0.82
    Activations Density 0.019%

    No Known Activations