© 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. 42308
    Prev
    Next
    INDEX
    Explanations

    speakers

    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
     speakers
    -1.90
    speakers
    -1.36
     Speakers
    -1.32
    Speakers
    -1.25
     panelists
    -0.93
    ⓧ
    -0.90
     authors
    -0.82
    featureID
    -0.79
     presenters
    -0.77
     autorytatywna
    -0.74
    POSITIVE LOGITS
    市镇
    0.59
    hoots
    0.54
    SizeF
    0.51
    áli
    0.50
    khana
    0.49
    produzione
    0.47
    alez
    0.47
    vated
    0.47
    Auguste
    0.47
     Arque
    0.46
    Activations Density 0.107%

    No Known Activations