© 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. 20-CLT-HP
    7. 72187
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    np_max-act-logits · 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
    Personendaten
    -0.65
    ]}"
    -0.57
     дописавши
    -0.51
     variabel
    -0.51
    elemField
    -0.49
    HtmlAttribute
    -0.49
    OGND
    -0.48
    asının
    -0.47
    ensdag
    -0.47
     penuh
    -0.47
    POSITIVE LOGITS
     Indemnity
    0.57
    NewReader
    0.54
    TagMode
    0.53
    uisine
    0.49
     hadapan
    0.49
    lusconi
    0.49
    marck
    0.45
    ItemBackground
    0.45
     matel
    0.45
     tristesse
    0.45
    Activations Density 0.001%

    No Known Activations