© 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. 91191
    Prev
    Next
    INDEX
    Explanations

    themselves

    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
     themselves
    -1.56
    themselves
    -1.13
     their
    -0.72
     "
    -0.56
     me
    -0.56
     “
    -0.54
     deres
    -0.54
    Their
    -0.54
    ↵↵
    -0.52
     Their
    -0.52
    POSITIVE LOGITS
    endphp
    1.38
     متعلقه
    1.26
     CreateTagHelper
    1.20
    expandindo
    1.19
    WriteTagHelper
    1.18
     виправивши
    1.13
    AndEndTag
    1.12
    SourceChecksum
    1.10
    adaptiveStyles
    1.09
    URLException
    1.09
    Activations Density 0.125%

    No Known Activations