© 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. 2-RES-MATRYOSHKA-DC
    7. 3861
    Prev
    Next
    INDEX
    Explanations

    references to political campaigns and candidates

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMPORTED
    -0.48
    </table>
    -0.45
    SizeF
    -0.44
    AddHtmlAttribute
    -0.42
     Flow
    -0.42
    ≦)
    -0.41
    Datuak
    -0.40
    unitOfWork
    -0.40
    beiter
    -0.39
     fö
    -0.38
    POSITIVE LOGITS
     candidates
    0.81
     candidacy
    0.80
     candidate
    0.75
     primaries
    0.72
    quiao
    0.71
     Shakspeare
    0.70
    Personendaten
    0.69
    ⓧ
    0.68
     Candidates
    0.67
     väli
    0.67
    Activations Density 0.769%

    No Known Activations