© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45969
    Prev
    Next
    INDEX
    Explanations

    Uncertainty or continued existence

    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
    setVerticalGroup
    -0.81
    \{\\
    -0.75
    WaitGroup
    -0.75
    
    -0.74
     Exactos
    -0.73
     الحره
    -0.68
    ########.
    -0.67
    BASEPATH
    -0.67
     >=",
    -0.66
    $_['
    -0.65
    POSITIVE LOGITS
     to
    0.67
     the
    0.51
     is
    0.50
    shmi
    0.49
     was
    0.48
     Anlass
    0.45
    اضي
    0.44
     what
    0.44
    ことから
    0.43
     ta
    0.42
    Activations Density 0.085%

    No Known Activations