© 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. 5-CLT-HP
    7. 3709
    Prev
    Next
    INDEX
    Explanations

    Time

    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
    #+#
    -0.75
    saraba
    -0.72
    исленность
    -0.67
    Населення
    -0.61
     kteří
    -0.61
    ExtendWith
    -0.54
    Życiorys
    -0.54
    AddWithValue
    -0.53
     LIABLE
    -0.53
    Autoritní
    -0.52
    POSITIVE LOGITS
     now
    0.71
     it
    0.66
     recently
    0.59
     anyway
    0.58
     in
    0.58
     sometime
    0.54
    recently
    0.54
    脚注の使い方
    0.53
     lately
    0.53
     earlier
    0.48
    Activations Density 0.001%

    No Known Activations