© 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. 12-RES-MATRYOSHKA-DC
    7. 30415
    Prev
    Next
    INDEX
    Explanations

    phrases discussing proportions and proportional relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     وتسجيلات
    -0.80
    /***/
    -0.71
    ไล
    -0.66
    ++];
    -0.65
     age
    -0.64
    CharStream
    -0.64
     mwaka
    -0.63
     Wicidata
    -0.62
     Kays
    -0.62
    uesia
    -0.60
    POSITIVE LOGITS
     Proportion
    1.03
    Proportion
    0.95
    proportion
    0.90
     proportionality
    0.88
     Propor
    0.86
    propor
    0.80
     disproportion
    0.80
    parseColor
    0.77
     Masson
    0.76
     proportioned
    0.76
    Activations Density 0.013%

    No Known Activations