© 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. 0-CLT-HP
    7. 41307
    Prev
    Next
    INDEX
    Explanations

    mood/depression

    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
     mood
    -1.02
    mood
    -0.87
     propOrder
    -0.81
    BufferException
    -0.79
     Mood
    -0.77
    OGND
    -0.75
     Stimmung
    -0.75
    ulipas
    -0.73
    Mood
    -0.72
    tvguidetime
    -0.71
    POSITIVE LOGITS
    a
    0.47
    exitRule
    0.45
    REMOV
    0.45
    e
    0.45
     <<<<<<<<<<<<<<
    0.44
    ed
    0.42
    #!/
    0.41
    emia
    0.41
    obiology
    0.41
    άρ
    0.40
    Activations Density 0.606%

    No Known Activations