© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 560
    Prev
    Next
    INDEX
    Explanations

    time references

    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
    ↵
    -0.52
     yıld
    -0.48
    |
    -0.44
    !
    -0.43
     
    -0.42
    i
    -0.39
     sentirse
    -0.39
     indruk
    -0.39
     yaklaş
    -0.38
    <eos>
    -0.37
    POSITIVE LOGITS
    帖最后由
    1.14
    WithIOException
    0.93
    NUMX
    0.93
     CreateTagHelper
    0.91
     विश्वसनीयता
    0.91
    DockStyle
    0.90
    Personendaten
    0.88
     متعلقه
    0.86
    ();)
    0.85
     consultato
    0.82
    Activations Density 0.031%

    No Known Activations