© 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. 5-CLT-HP
    7. 3423
    Prev
    Next
    INDEX
    Explanations

    y

    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
     مشين
    -0.60
    doctype
    -0.57
    cipar
    -0.57
    Enllaces
    -0.57
    AutoField
    -0.57
    antd
    -0.51
    __':
    -0.48
     vestiti
    -0.48
     calculées
    -0.48
     bezeichneter
    -0.47
    POSITIVE LOGITS
     оригіналу
    0.74
     signing
    0.68
    CodedInputStream
    0.65
    InjectAttribute
    0.64
    <?
    0.62
     agreements
    0.57
     smlou
    0.56
     signer
    0.54
     Forts
    0.54
     humo
    0.53
    Activations Density 0.000%

    No Known Activations