© 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. 22300
    Prev
    Next
    INDEX
    Explanations

    the prefix "tri," which suggests a focus on terms related to trivalent compounds or groups

    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
    --
    -0.82
     defaultstate
    -0.79
     |
    -0.76
    _
    -0.75
    anker
    -0.72
    ')";
    -0.72
    ')")
    -0.71
     ){
    -0.69
    ".
    -0.68
    )*/
    -0.68
    POSITIVE LOGITS
    tri
    1.10
     tri
    1.09
    Tri
    1.09
     Tri
    1.06
     tricycle
    0.96
     Tripoli
    0.94
     TRI
    0.90
    TRI
    0.90
     triangulation
    0.87
    Tril
    0.85
    Activations Density 0.007%

    No Known Activations