© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4419
    Prev
    Next
    INDEX
    Explanations

    suicide

    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
    setGeometry
    -0.60
    irlo
    -0.48
     civi
    -0.48
    ERVIS
    -0.47
    ariki
    -0.46
     >=",
    -0.45
    verlauf
    -0.45
    lovakia
    -0.44
    tières
    -0.44
     Distribu
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.81
    SpringBootTest
    0.59
    BeginContext
    0.59
    tagHelperRunner
    0.59
    ArgsConstructor
    0.57
     aapt
    0.55
    TargetException
    0.54
    Rhestr
    0.54
    BASEPATH
    0.54
    fortawesome
    0.53
    Activations Density 0.001%

    No Known Activations