© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93358
    Prev
    Next
    INDEX
    Explanations

    Particle/Party

    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
     Particles
    -1.34
     particle
    -1.30
     particles
    -1.24
     Party
    -1.23
    Party
    -1.23
     party
    -1.23
     Particle
    -1.20
    party
    -1.20
     PARTY
    -1.17
    Particles
    -1.13
    POSITIVE LOGITS
     Drapeau
    0.60
    PINES
    0.55
    stawa
    0.54
    <bos>
    0.51
     hacks
    0.51
     estimés
    0.50
     mellitus
    0.50
    abetes
    0.49
     bypassing
    0.48
    inaudible
    0.47
    Activations Density 0.058%

    No Known Activations