© 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. 32083
    Prev
    Next
    INDEX
    Explanations

    words related to the nose and nasal health

    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
    tamen
    -0.69
     Graff
    -0.65
    Johanna
    -0.64
    slots
    -0.63
     cytok
    -0.61
    MCA
    -0.61
     Felton
    -0.61
     Stephanie
    -0.60
     Edelman
    -0.59
     
    -0.59
    POSITIVE LOGITS
     nose
    1.48
     Nose
    1.48
     Nas
    1.41
    Nas
    1.39
    Nose
    1.37
     noses
    1.37
     Nase
    1.36
     Nasal
    1.26
     NAS
    1.21
    nose
    1.20
    Activations Density 0.010%

    No Known Activations