© 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. 11509
    Prev
    Next
    INDEX
    Explanations

    utum

    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
     useState
    -0.52
     upper
    -0.51
    aup
    -0.50
     FAT
    -0.48
    JsonProperty
    -0.48
     Alber
    -0.48
    grow
    -0.47
     Upper
    -0.47
    ساب
    -0.47
    ImageBackground
    -0.47
    POSITIVE LOGITS
     wireType
    0.69
     SqlCommand
    0.60
     ComVisible
    0.59
     nakalista
    0.59
     kasarigan
    0.58
    SpringBootTest
    0.58
    MIDDLEWARE
    0.56
    Portály
    0.56
     '-':
    0.56
     pinulongan
    0.56
    Activations Density 0.007%

    No Known Activations