© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93527
    Prev
    Next
    INDEX
    Explanations

    a

    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
    しまう
    -0.45
    <eos>
    -0.40
     while
    -0.40
    uset
    -0.40
     sementara
    -0.40
    Lähteet
    -0.39
     mãi
    -0.39
    য়
    -0.39
    st
    -0.37
     poži
    -0.37
    POSITIVE LOGITS
    ReusableCell
    0.92
    sizeCache
    0.88
     JpaRepository
    0.83
     CascadeType
    0.81
     InputDecoration
    0.81
    featureID
    0.81
    \{\\
    0.78
     MainAxisSize
    0.77
    存于互联网档案馆
    0.76
    DockStyle
    0.76
    Activations Density 0.001%

    No Known Activations