© 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. 9600
    Prev
    Next
    INDEX
    Explanations

    structured data and code snippets indicating a query or command format

    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
     Kindheit
    -0.53
    ouard
    -0.50
    kuuta
    -0.50
    estudio
    -0.47
    wärts
    -0.44
    etsk
    -0.42
    раздо
    -0.42
    otle
    -0.42
     submit
    -0.42
    acia
    -0.42
    POSITIVE LOGITS
    AlterField
    0.74
    IntoConstraints
    0.72
     AssemblyCulture
    0.72
     CreateTagHelper
    0.69
    IsContent
    0.69
    dafx
    0.67
    AndroidJUnit
    0.67
     propOrder
    0.65
    RTLR
    0.65
    RetentionPolicy
    0.63
    Activations Density 0.061%

    No Known Activations