© 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. 15112
    Prev
    Next
    INDEX
    Explanations

    general-purpose 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
    TagMode
    -0.80
    RegistryLite
    -0.68
    httphttps
    -0.68
    horabuena
    -0.66
    PerformLayout
    -0.63
     invokingState
    -0.60
    SharedDtor
    -0.59
     Chwiliwch
    -0.58
    QtWidgets
    -0.56
    ofs
    -0.56
    POSITIVE LOGITS
     embryo
    0.48
     censi
    0.47
     bench
    0.47
    rawtypes
    0.45
     Accountant
    0.45
     Macca
    0.44
     Quasi
    0.44
     descriptors
    0.44
     Tah
    0.44
     Polity
    0.43
    Activations Density 0.011%

    No Known Activations