© 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. 5-CLT-HP
    7. 91474
    Prev
    Next
    INDEX
    Explanations

    political parties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragalactic
    -0.82
    tvguidetime
    -0.77
     препратки
    -0.69
    رشف
    -0.68
    IsContent
    -0.65
     Савезне
    -0.63
    WebVitals
    -0.62
    <bos>
    -0.62
     AssemblyVersion
    -0.60
     }</
    -0.59
    POSITIVE LOGITS
     Party
    0.66
     party
    0.65
    Party
    0.57
     Partei
    0.50
    party
    0.43
     Union
    0.43
     PARTY
    0.42
     Palt
    0.42
     Association
    0.41
    findpost
    0.38
    Activations Density 0.025%

    No Known Activations