© 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. 93048
    Prev
    Next
    INDEX
    Explanations

    therapy

    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
    therapy
    -1.64
     Therapy
    -1.55
     therapy
    -1.52
    Therapy
    -1.50
     THERAPY
    -1.50
     Therapist
    -1.20
    therap
    -1.20
     Therap
    -1.19
     therapist
    -1.15
     therapists
    -1.12
    POSITIVE LOGITS
     congratulate
    0.55
     fugitive
    0.54
     congratulations
    0.52
    ھو
    0.52
     responses
    0.51
     hold
    0.50
     ê
    0.49
     movements
    0.48
     achievements
    0.48
    Congratulations
    0.48
    Activations Density 0.109%

    No Known Activations