© 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. 0-CLT-HP
    7. 40012
    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
     suicide
    -1.74
    suicide
    -1.36
     Suicide
    -1.22
     suicidal
    -1.16
     suicides
    -1.12
    Suicide
    -1.05
     suic
    -1.00
     suicidio
    -0.82
    oc
    -0.81
    mo
    -0.75
    POSITIVE LOGITS
    MessageOf
    0.50
     TestBed
    0.47
    saga
    0.42
     pacchetto
    0.42
     arrivato
    0.41
     plátano
    0.41
     pimienta
    0.40
    ^{[
    0.40
    constructor
    0.39
     <",
    0.39
    Activations Density 1.787%

    No Known Activations