© 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. 9844
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and accomplishment

    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
    Composable
    -0.71
     Bellini
    -0.64
     sweeteners
    -0.63
    /<
    -0.60
    Dior
    -0.60
     Varan
    -0.59
     Elisha
    -0.59
     aper
    -0.59
    Salle
    -0.58
     skiers
    -0.58
    POSITIVE LOGITS
    proud
    1.39
     proud
    1.38
     pride
    1.31
     Proud
    1.29
     stolz
    1.26
     Pride
    1.20
     orgull
    1.18
    pride
    1.17
    Proud
    1.14
    Pride
    1.13
    Activations Density 0.007%

    No Known Activations