© 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. 29071
    Prev
    Next
    INDEX
    Explanations

    terms related to political endorsements

    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
    kegaard
    -0.77
     VIAF
    -0.76
     automó
    -0.76
     Blak
    -0.75
    ientôt
    -0.69
     Réponses
    -0.69
    rafty
    -0.69
    รก
    -0.68
     setDescription
    -0.68
    ึก
    -0.68
    POSITIVE LOGITS
     endorsed
    1.45
     endorse
    1.44
     Endor
    1.42
     endorsements
    1.41
     endorsement
    1.38
    endor
    1.30
    orses
    1.27
    Endor
    1.26
     endorsing
    1.23
     Dor
    1.14
    Activations Density 0.003%

    No Known Activations