© 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. 5-CLT-HP
    4. 1231
    Prev
    Next
    INDEX
    Explanations

    then

    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
    /}{
    -0.54
    &=&
    -0.53
    &=&\
    -0.52
    >"
    -0.50
    Affirmed
    -0.49
    //}
    
    -0.49
    /"
    -0.48
    //}
    -0.48
     #"
    -0.48
    shtml
    -0.46
    POSITIVE LOGITS
    ,
    0.94
     I
    0.85
    aarrggbb
    0.77
    InstanceState
    0.75
     '\\;'
    0.68
    WarningLevel
    0.66
    HasForeignKey
    0.62
    Personensuche
    0.60
    I
    0.56
     يتيمه
    0.56
    Activations Density 0.000%

    No Known Activations