© 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. 22-RES-MATRYOSHKA-DC
    7. 2917
    Prev
    Next
    INDEX
    Explanations

    passages discussing imaging techniques such as microscopy and other methods related to magnetism

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     analysis
    -0.69
    ="@+
    -0.69
     analyses
    -0.68
     tests
    -0.65
    analysis
    -0.64
     examination
    -0.59
     analyzes
    -0.59
    analyses
    -0.59
     AssemblyCulture
    -0.58
    ViewImports
    -0.57
    POSITIVE LOGITS
    varande
    0.49
     neutrons
    0.49
    Дереккөздер
    0.49
    
    0.49
    beat
    0.48
     gynnwys
    0.47
     interstitial
    0.47
    gemeinschaft
    0.46
    acchar
    0.46
    Companion
    0.46
    Activations Density 0.228%

    No Known Activations