© 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. 4-CLT-HP
    7. 251
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     CURIAM
    -0.69
     nakalista
    -0.57
     AssemblyCulture
    -0.55
    __":
    -0.51
    AttributeSet
    -0.50
    AndEndTag
    -0.49
    PhysRevD
    -0.49
    Bes
    -0.49
     "..\..\..\
    -0.48
    assertRaises
    -0.47
    POSITIVE LOGITS
     againſt
    0.57
    RTDA
    0.57
     oars
    0.57
     سكانية
    0.57
    łoży
    0.54
    IndentedString
    0.54
     thunk
    0.53
    Personendaten
    0.53
    ItemBackground
    0.52
     gând
    0.51
    Activations Density 0.002%

    No Known Activations