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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5010
    Prev
    Next
    INDEX
    Explanations

    therapeutic

    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
    ]--;
    -0.60
     Picchu
    -0.58
    ]='\
    -0.57
     المعيارى
    -0.54
    󠁴
    -0.50
    setof
    -0.49
    évaluateur
    -0.49
    /*
    -0.49
    例句
    -0.49
    rétaire
    -0.48
    POSITIVE LOGITS
    المناصب
    0.63
     فہرست
    0.54
    DockStyle
    0.52
    haka
    0.51
    praš
    0.50
    MigrationBuilder
    0.49
    indd
    0.49
    ijnt
    0.48
     Gulf
    0.48
     елның
    0.48
    Activations Density 0.005%

    No Known Activations