© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45812
    Prev
    Next
    INDEX
    Explanations

    thal

    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
    thal
    -0.80
     (
    -0.55
     and
    -0.55
    ,
    -0.52
    .
    -0.52
     a
    -0.50
     h
    -0.50
     #
    -0.49
    )
    -0.48
     due
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    1.23
     Houſe
    0.87
    Демографія
    0.86
     bParam
    0.86
     nonUne
    0.86
     photolibrary
    0.82
    ^(@)
    0.82
     getRule
    0.82
     ―――――
    0.82
    Tikang
    0.81
    Activations Density 0.006%

    No Known Activations