© 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. 5-CLT-HP
    4. 3256
    Prev
    Next
    INDEX
    Explanations

    is

    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
     tính
    -0.47
     way
    -0.45
     too
    -0.40
     WAY
    -0.40
     Way
    -0.39
     sais
    -0.39
    nak
    -0.38
    akit
    -0.38
    liosis
    -0.37
     at
    -0.36
    POSITIVE LOGITS
     pinulongan
    1.14
    Datuak
    0.98
    Personendaten
    0.96
    InitVars
    0.95
    ftagPool
    0.93
    AndEndTag
    0.93
     صوتيه
    0.91
    المناصب
    0.84
    LookAnd
    0.82
     يتيمه
    0.82
    Activations Density 0.002%

    No Known Activations