© 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. 5-CLT-HP
    7. 5361
    Prev
    Next
    INDEX
    Explanations

    Drilling, Technical Texts

    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
    rungsseite
    -0.80
     invokingState
    -0.69
    RegistryLite
    -0.69
    tanleria
    -0.67
     Autorizaciones
    -0.65
     ujednoznacz
    -0.64
    tvguidetime
    -0.63
     estimés
    -0.62
    SharedCtor
    -0.62
    хьтан
    -0.62
    POSITIVE LOGITS
     Policy
    0.51
     a
    0.51
     for
    0.50
     to
    0.50
     out
    0.49
     Unit
    0.48
    žas
    0.47
     Loan
    0.47
     Newell
    0.47
    unità
    0.46
    Activations Density 0.000%

    No Known Activations