© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2460
    Prev
    Next
    INDEX
    Explanations

    a mix of foreign language and movie titles

    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
    DockStyle
    -0.68
    الحياه
    -0.57
    matcher
    -0.53
    صلاح
    -0.52
    Tier
    -0.50
    textTheme
    -0.49
    arci
    -0.49
     Shall
    -0.48
     bothered
    -0.48
     Saver
    -0.48
    POSITIVE LOGITS
     resourceCulture
    0.70
    +#+
    0.68
     allAfrica
    0.54
    complexType
    0.52
    queryInterface
    0.52
     générales
    0.48
    TypedDataSet
    0.48
    Tikang
    0.47
    imageio
    0.47
    SourceChecksum
    0.47
    Activations Density 0.017%

    No Known Activations