© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a desire to believe in unrealistic or idealized notions

    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
    IntoConstraints
    -1.04
     Efq
    -0.93
     Jefus
    -0.85
     متعلقه
    -0.83
     GenerationType
    -0.82
     itſelf
    -0.82
     perpetuity
    -0.81
    bibfield
    -0.79
     Houſe
    -0.78
     Monfieur
    -0.75
    POSITIVE LOGITS
     kết
    0.38
     initial
    0.38
    ;
    0.36
     part
    0.36
    .
    0.36
    ↵↵
    0.35
    bab
    0.35
    raz
    0.35
     bab
    0.35
    Pyx
    0.35
    Activations Density 0.123%

    No Known Activations