© 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. 24-RES-MATRYOSHKA-DC
    7. 1185
    Prev
    Next
    INDEX
    Explanations

    discussions of the benefits of something in a health or environment context

    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
    +#+#
    -0.73
    GHIJKLM
    -0.56
    
    -0.56
     esternos
    -0.54
     strict
    -0.51
    Strict
    -0.50
     Strict
    -0.49
     intolerance
    -0.48
    labus
    -0.48
     AssemblyCulture
    -0.48
    POSITIVE LOGITS
     benefits
    1.95
     benefit
    1.88
    benefits
    1.62
    benefit
    1.57
     Benefits
    1.46
     gains
    1.44
     BENEFITS
    1.44
     advantages
    1.43
     Benefit
    1.41
     avantages
    1.41
    Activations Density 1.690%

    No Known Activations