© 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. 12-RES-MATRYOSHKA-DC
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    assignments involving the variable 'rot' and iterations or increments related to counting or looping structures

    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
    Negative Logits
     CreateTagHelper
    -0.60
    uestamente
    -0.49
     credere
    -0.48
    NewGuid
    -0.46
    TabStop
    -0.45
     lisää
    -0.44
     here
    -0.44
    esanan
    -0.44
     tiet
    -0.42
    onNext
    -0.42
    POSITIVE LOGITS
    scriptcase
    0.80
     оригіналу
    0.80
     الحره
    0.77
     فريبيس
    0.76
    +:+
    0.75
     linkovi
    0.73
    migrationBuilder
    0.71
    findpost
    0.70
     الدولى
    0.70
     "..\..\
    0.68
    Activations Density 0.004%

    No Known Activations