© 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. 29833
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages, as well as patterns related to numerical sequences

    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
    LookAnd
    -0.94
     <<<<<<<<<<<<<<
    -0.80
     HasFactory
    -0.79
     InputDecoration
    -0.75
     calendriers
    -0.75
    AutoScaleMode
    -0.74
     يتيمه
    -0.72
    SpringBootTest
    -0.71
    #+#
    -0.70
     CascadeType
    -0.69
    POSITIVE LOGITS
    ngrx
    0.44
    tiskt
    0.40
     horaires
    0.40
     `
    0.40
     .
    0.39
    ERIE
    0.39
    な
    0.39
     ‘
    0.39
    scrollTo
    0.39
    inois
    0.39
    Activations Density 0.040%

    No Known Activations