© 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. 18-RES-MATRYOSHKA-DC
    7. 928
    Prev
    Next
    INDEX
    Explanations

    data sets and parameters used in machine learning

    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.18.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.18.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
    istoitu
    -0.66
    EndInit
    -0.59
    ngdoc
    -0.58
    abestanden
    -0.57
    __*/
    -0.54
    
    -0.45
    rawtypes
    -0.45
     rent
    -0.45
    trane
    -0.43
     combineReducers
    -0.43
    POSITIVE LOGITS
     Jefus
    0.64
     Chriftian
    0.61
     decays
    0.59
     sandero
    0.59
     Scand
    0.58
     ťaž
    0.56
     decay
    0.56
     production
    0.56
     Monfieur
    0.56
     Beller
    0.55
    Activations Density 0.781%

    No Known Activations