© 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. 25242
    Prev
    Next
    INDEX
    Explanations

    numeric values and their statistical representations

    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
    Negative Logits
    AnimationsModule
    -0.85
     Efq
    -0.85
     ſtate
    -0.82
     ftate
    -0.82
    IContainer
    -0.79
    RTEE
    -0.79
    SpringRunner
    -0.78
     raiſ
    -0.77
     holotype
    -0.76
    UIControlState
    -0.75
    POSITIVE LOGITS
    </h6>
    0.52
     ج
    0.50
    ku
    0.46
    umel
    0.44
     Mit
    0.44
     }_{
    0.43
    udi
    0.43
    わが
    0.42
    نا
    0.42
     Labor
    0.42
    Activations Density 0.007%

    No Known Activations