© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43487
    Prev
    Next
    INDEX
    Explanations

    phosphat

    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
    ly
    -0.83
    tin
    -0.66
     مشين
    -0.64
     Chel
    -0.59
    ⓧ
    -0.59
     poo
    -0.57
     ourselves
    -0.56
    phosphat
    -0.55
    lec
    -0.54
     settler
    -0.53
    POSITIVE LOGITS
    hibe
    0.63
    kháu
    0.60
    raszamy
    0.59
    raded
    0.57
     stanovnika
    0.57
    addImage
    0.55
    pearing
    0.54
    ControllerTest
    0.52
    poque
    0.51
    metheus
    0.51
    Activations Density 0.178%

    No Known Activations