© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 249
    Prev
    Next
    INDEX
    Explanations

    references to political parties and elections, especially regarding the Democratic and Green parties.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     Propriet
    -0.54
     فريبيس
    -0.53
     ГУ
    -0.50
    ழ்
    -0.49
    idelberg
    -0.47
    isseurs
    -0.47
     MOQ
    -0.46
     GTR
    -0.46
     planten
    -0.44
     arbo
    -0.44
    POSITIVE LOGITS
     election
    1.44
     political
    1.34
     voters
    1.34
     Election
    1.33
     voter
    1.28
     candidate
    1.28
     electorate
    1.23
     elections
    1.21
     electoral
    1.21
     candidates
    1.20
    Activations Density 3.096%

    No Known Activations