© 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. 0-CLT-HP
    7. 97361
    Prev
    Next
    INDEX
    Explanations

    killer

    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
     killer
    -1.59
     murderer
    -1.48
    killer
    -1.45
     killers
    -1.40
     murderers
    -1.35
     Killer
    -1.31
     criminal
    -1.30
    criminal
    -1.27
    Criminal
    -1.16
    Killer
    -1.14
    POSITIVE LOGITS
     ویکی‌پدی
    0.66
    gettes
    0.65
    ReusableCell
    0.64
    GeneratedCode
    0.62
    agerie
    0.61
     jScrollPane
    0.61
    abilia
    0.59
    ividual
    0.58
    crisy
    0.57
    ])):
    0.57
    Activations Density 0.084%

    No Known Activations