© 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. 44038
    Prev
    Next
    INDEX
    Explanations

    toxin

    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
     toxin
    -2.08
     toxins
    -1.92
    toxin
    -1.77
    toxins
    -1.66
     toxicity
    -1.52
     toxic
    -1.43
     Tox
    -1.41
    Toxic
    -1.40
     Toxic
    -1.38
    toxic
    -1.37
    POSITIVE LOGITS
    ,
    0.73
     (
    0.68
     Mar
    0.65
     in
    0.63
     and
    0.62
     E
    0.59
     Les
    0.59
     "
    0.58
    ies
    0.58
     inter
    0.57
    Activations Density 0.296%

    No Known Activations