© 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. 25537
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest implications or associations about statements and beliefs

    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
     devenus
    -0.66
    ReusableCell
    -0.66
     becauſe
    -0.65
     ſeveral
    -0.65
    empereur
    -0.62
     whoſe
    -0.62
    IBOutlet
    -0.61
     endregion
    -0.61
     scolaires
    -0.60
     LIRE
    -0.60
    POSITIVE LOGITS
     implies
    0.66
     implying
    0.56
     implied
    0.56
     imply
    0.56
     assumes
    0.50
     implication
    0.50
    opardi
    0.50
     presume
    0.48
     assume
    0.45
     implicitly
    0.45
    Activations Density 0.155%

    No Known Activations