© 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. 23105
    Prev
    Next
    INDEX
    Explanations

    various forms of numerical values, possibly for referencing measurements or results in scientific contexts

    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
       
    -0.48
    fair
    -0.47
    ,
    -0.46
    !
    -0.46
     is
    -0.45
     <<<<<<<<<<<<<<
    -0.44
      
    -0.44
     (
    -0.44
     Khalil
    -0.44
     tématu
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    1.00
    rungsseite
    0.86
     بيها
    0.84
    %";
    0.83
     ―――――
    0.81
    UpInside
    0.79
    ."</
    0.79
     useAppContext
    0.78
    oredCriteria
    0.78
    ็จ
    0.75
    Activations Density 0.008%

    No Known Activations