© 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. 14816
    Prev
    Next
    INDEX
    Explanations

    patterns in statistical results related to research findings

    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
     snippetHide
    -0.76
    ulario
    -0.74
    Personensuche
    -0.73
    #+#
    -0.72
    :]:
    -0.71
    "):
    -0.70
    脚注の使い方
    -0.69
    ContentAsync
    -0.68
    ]]:
    -0.67
    Initializable
    -0.67
    POSITIVE LOGITS
    homonymie
    0.60
     souri
    0.50
     diplomas
    0.50
     henkilö
    0.49
     iprot
    0.47
     configurer
    0.47
     configureStore
    0.46
    cipar
    0.46
     seura
    0.45
     recev
    0.44
    Activations Density 0.025%

    No Known Activations