© 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. 6285
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanation or clarification

    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
     Hickey
    -0.76
    arkas
    -0.75
    RegistryLite
    -0.69
    ]")]
    -0.69
    firestore
    -0.68
     fó
    -0.67
    tagHelper
    -0.66
     MyBatis
    -0.65
    writerow
    -0.64
     Dorsey
    -0.63
    POSITIVE LOGITS
    lanations
    1.55
     explain
    1.53
    explain
    1.53
     Explain
    1.51
     explanation
    1.46
     explained
    1.45
     Explanation
    1.41
    Explain
    1.41
     Explained
    1.41
     explains
    1.38
    Activations Density 0.048%

    No Known Activations