© 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. 22-RES-MATRYOSHKA-DC
    7. 1432
    Prev
    Next
    INDEX
    Explanations

    words related to elections

    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.22.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.22.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
     destroyers
    -0.53
    antaine
    -0.48
    GCG
    -0.47
    RectangleBorder
    -0.44
    ecap
    -0.43
     compres
    -0.42
    JMenuBar
    -0.42
     hedef
    -0.41
    chyma
    -0.41
     ***!
    -0.40
    POSITIVE LOGITS
     vote
    2.17
     voting
    2.09
     votes
    2.00
     election
    1.98
     voter
    1.98
     ballot
    1.92
     voters
    1.89
     Election
    1.82
     elections
    1.82
    vote
    1.82
    Activations Density 0.952%

    No Known Activations