© 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. 5-CLT-HP
    7. 96707
    Prev
    Next
    INDEX
    Explanations

    People

    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
    ReusableCell
    -0.58
    didn
    -0.53
    binaan
    -0.50
     '\\;'
    -0.49
     possibles
    -0.48
    appeared
    -0.48
     tutt
    -0.48
    MockBean
    -0.47
     kaynağından
    -0.47
    forChild
    -0.47
    POSITIVE LOGITS
    __':
    0.59
    ']))
    0.54
    DoubleQuotes
    0.54
     estekak
    0.52
    '])->
    0.52
    kháu
    0.51
     =>
    0.50
    ceton
    0.50
    __":
    0.50
    CGRectMake
    0.50
    Activations Density 0.001%

    No Known Activations