© 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. 12231
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and shared experiences

    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
     ourselves
    -0.87
     myself
    -0.58
     nossa
    -0.57
     Myself
    -0.50
     our
    -0.49
    тим
    -0.48
     am
    -0.47
    myself
    -0.47
    sp
    -0.46
    our
    -0.46
    POSITIVE LOGITS
    sizeCache
    0.99
     '\\;'
    0.96
    SourceChecksum
    0.93
    CloseOperation
    0.88
     ostavi
    0.85
     CreateTagHelper
    0.84
    FunctionFlags
    0.83
    تقاوى
    0.83
     Paglinawan
    0.83
    OGND
    0.81
    Activations Density 0.057%

    No Known Activations