© 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. 5-CLT-HP
    7. 1195
    Prev
    Next
    INDEX
    Explanations

    feelings

    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
     hjemme
    -0.65
     mergeFrom
    -0.65
    PerformLayout
    -0.63
     itſelf
    -0.59
    تقاوى
    -0.57
    zbęd
    -0.54
     sólido
    -0.54
     Monfieur
    -0.54
     virkelig
    -0.51
     réparer
    -0.50
    POSITIVE LOGITS
     state
    0.77
     brain
    0.70
     mood
    0.68
     mind
    0.66
    state
    0.60
     minds
    0.59
     muscles
    0.59
     demeanor
    0.58
     feeling
    0.58
     eyes
    0.58
    Activations Density 0.001%

    No Known Activations