© 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. 0-CLT-HP
    7. 43337
    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
     Party
    -1.03
     PARTY
    -0.84
    Party
    -0.82
     Deal
    -0.82
    脚注の使い方
    -0.76
     DEAL
    -0.74
    Deal
    -0.73
    PARTY
    -0.73
    deal
    -0.71
    party
    -0.70
    POSITIVE LOGITS
     exiles
    0.58
     liberi
    0.56
     restored
    0.53
     toscana
    0.53
     proste
    0.52
     awakens
    0.52
     libero
    0.51
    <bos>
    0.49
     anthropologists
    0.49
     schia
    0.49
    Activations Density 0.448%

    No Known Activations