© 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. 6078
    Prev
    Next
    INDEX
    Explanations

    instances of hypocrisy and contradictions in people's statements and actions

    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
    ########.
    -0.61
    thenReturn
    -0.48
    StructEnd
    -0.47
    TypedDataSet
    -0.45
    первых
    -0.45
    fjspx
    -0.43
    ArrowToggle
    -0.41
    isome
    -0.41
    ysty
    -0.41
    HTTPClient
    -0.40
    POSITIVE LOGITS
     myself
    1.09
     himself
    1.07
     herself
    1.04
    himself
    1.01
    herself
    1.00
     yourself
    0.99
     personally
    0.96
     own
    0.95
     thyself
    0.93
    自分も
    0.92
    Activations Density 0.585%

    No Known Activations