© 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. 1085
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in scientific papers when discussing the design of experiments and analysing their results

    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
    enumii
    -0.65
     للمعارف
    -0.50
     թվական
    -0.50
     resourceCulture
    -0.49
    REME
    -0.48
    первых
    -0.47
    ViewFeatures
    -0.47
    zco
    -0.46
    avax
    -0.46
     costs
    -0.44
    POSITIVE LOGITS
     influence
    1.71
     influences
    1.68
     determines
    1.65
     influencing
    1.63
     determine
    1.62
     determining
    1.57
    influence
    1.55
    Influence
    1.53
     Influence
    1.52
    influ
    1.50
    Activations Density 1.557%

    No Known Activations