© 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. 22533
    Prev
    Next
    INDEX
    Explanations

    references to scientific investigation and research methodology related to quantum systems

    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
     lī
    -0.46
    Source
    -0.45
     evidence
    -0.45
    Data
    -0.44
     cause
    -0.44
     observation
    -0.43
    fact
    -0.42
     Dro
    -0.42
     prove
    -0.42
    DAT
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    0.86
     GenerationType
    0.81
    tagHelperRunner
    0.78
     initComponents
    0.76
     ExecuteAsync
    0.76
    EndInit
    0.73
    ftagPool
    0.71
     MonoBehaviour
    0.71
    findpost
    0.70
    wieś
    0.70
    Activations Density 0.096%

    No Known Activations