© 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. 24-RES-MATRYOSHKA-DC
    7. 1268
    Prev
    Next
    INDEX
    Explanations

    mentions of reducing costs, time, or space required

    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.24.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.24.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
    Personendaten
    -0.69
     pinulongan
    -0.68
    ScopeManager
    -0.63
    Personensuche
    -0.63
    WebServlet
    -0.62
    MENAFN
    -0.56
    
    -0.53
    AndEndTag
    -0.52
    änomen
    -0.51
    ingang
    -0.51
    POSITIVE LOGITS
     costs
    1.84
     cost
    1.77
    costs
    1.53
     expense
    1.49
     Costs
    1.47
     expenses
    1.46
    cost
    1.44
    Costs
    1.38
    Cost
    1.34
     Cost
    1.33
    Activations Density 1.525%

    No Known Activations