© 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. 21145
    Prev
    Next
    INDEX
    Explanations

    words related to trust and betrayal in a confrontational or survival context

    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
     m
    -0.44
    la
    -0.42
     ante
    -0.42
     
    -0.42
     Do
    -0.42
    chen
    -0.41
    Ignore
    -0.41
     i
    -0.41
    ${
    -0.41
     M
    -0.40
    POSITIVE LOGITS
     للمعارف
    1.16
     للاسماء
    0.95
     تانيه
    0.95
     myſelf
    0.88
    Personensuche
    0.88
     ſche
    0.82
     themſelves
    0.81
     fhew
    0.81
     Numerade
    0.79
     poffe
    0.79
    Activations Density 0.010%

    No Known Activations