© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14180
    Prev
    Next
    INDEX
    Explanations

    said

    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
     ujednoznacz
    -0.65
    EnableWeb
    -0.64
     inoxydable
    -0.63
    ὴν
    -0.62
    ANTLR
    -0.59
    espère
    -0.59
    ($__
    -0.58
     StatefulWidget
    -0.56
    ########.
    -0.54
    collants
    -0.53
    POSITIVE LOGITS
    complexContent
    0.47
    CodedInputStream
    0.44
    ifflin
    0.44
    bcryptjs
    0.43
    verifyException
    0.43
    XmlEnum
    0.42
    atigable
    0.41
     SEDS
    0.40
     ftill
    0.40
    ثة
    0.40
    Activations Density 0.005%

    No Known Activations