© 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. 26876
    Prev
    Next
    INDEX
    Explanations

    references to truth and its various interpretations

    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
    ing
    -0.66
    o
    -0.65
    addPreferredGap
    -0.63
    ené
    -0.58
    ená
    -0.58
    pdev
    -0.57
     anjo
    -0.57
    dyn
    -0.56
    appName
    -0.56
     Redmond
    -0.55
    POSITIVE LOGITS
     Truth
    1.37
     TRUTH
    1.25
    Truth
    1.23
    truth
    1.22
     truth
    1.16
     truths
    1.15
     Truths
    1.13
    fulness
    0.91
     Wahrheit
    0.90
     Tahu
    0.89
    Activations Density 0.005%

    No Known Activations