© 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. 15397
    Prev
    Next
    INDEX
    Explanations

    uc

    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
     sneeze
    -0.63
     sneezing
    -0.50
    getCause
    -0.49
    breviations
    -0.48
    ameters
    -0.47
    idez
    -0.45
    quement
    -0.44
    ctors
    -0.44
    GETHER
    -0.43
     Pots
    -0.43
    POSITIVE LOGITS
     дописавши
    0.67
    #+#
    0.66
     AssemblyCompany
    0.64
    Clik
    0.58
     okuyayım
    0.57
    Kaieteur
    0.57
    ########.
    0.56
    +#+
    0.54
    脚注の使い方
    0.54
    ℗
    0.52
    Activations Density 0.006%

    No Known Activations