© 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. 4-CLT-HP
    7. 3414
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    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
    thank
    -0.71
    ask
    -0.64
     dig
    -0.63
    thanks
    -0.63
    wow
    -0.62
    although
    -0.61
    however
    -0.61
    fjspx
    -0.61
     however
    -0.61
    Дереккөздер
    -0.61
    POSITIVE LOGITS
     sanitarias
    0.54
    expandindo
    0.48
     varandra
    0.46
     amores
    0.43
     sanitarios
    0.42
     själva
    0.42
     skjer
    0.42
     säs
    0.41
    VersionUID
    0.40
     gedacht
    0.40
    Activations Density 0.001%

    No Known Activations