© 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. 1-CLT-HP
    7. 14630
    Prev
    Next
    INDEX
    Explanations

    materials and chemical compounds

    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
    UMBIA
    -0.81
    بوابة
    -0.77
    اریخ
    -0.77
    Personendaten
    -0.77
     myſelf
    -0.76
    rawdź
    -0.75
    GEBURTSDATUM
    -0.75
     tranſ
    -0.75
     NavController
    -0.75
    WSGI
    -0.75
    POSITIVE LOGITS
     ser
    0.36
     же
    0.36
    ற
    0.34
     sé
    0.33
    AutoSize
    0.33
    f
    0.33
    …
    0.33
     soins
    0.32
    ...
    0.31
    fl
    0.31
    Activations Density 0.077%

    No Known Activations