© 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-RES-MATRYOSHKA-DC
    7. 14332
    Prev
    Next
    INDEX
    Explanations

    references to suicidal behavior or related terms

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.71
    AndEndTag
    -0.66
     FBref
    -0.64
    stretchr
    -0.60
    abetes
    -0.57
     reman
    -0.56
     Undead
    -0.55
     hereof
    -0.54
     esterno
    -0.54
    ValueStyle
    -0.54
    POSITIVE LOGITS
     suicide
    2.23
    suicide
    1.71
     Suicide
    1.52
    Suicide
    1.43
     suicides
    1.39
     suicidio
    0.96
     suicidal
    0.84
     suic
    0.74
    自杀
    0.73
    自殺
    0.72
    Activations Density 0.001%

    No Known Activations