© 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. 77845
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     referenties
    -0.81
    transQ
    -0.79
    Rhestr
    -0.79
    PerformLayout
    -0.72
    anyahu
    -0.68
     Efq
    -0.68
     esternos
    -0.67
    tvguidetime
    -0.67
     skak
    -0.66
    AnchorStyles
    -0.64
    POSITIVE LOGITS
     lèvres
    0.51
     några
    0.50
     fleste
    0.49
     frågan
    0.46
     modalità
    0.46
     hjemme
    0.46
     flesta
    0.45
     verksamhet
    0.45
     leçons
    0.45
     noen
    0.44
    Activations Density 0.000%

    No Known Activations