© 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. 2483
    Prev
    Next
    INDEX
    Explanations

    achieving, providing

    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
     الحره
    -0.67
    ]]
    -0.65
    '],
    -0.64
    ():
    -0.59
    endphp
    -0.58
    ​=
    -0.58
    Jîn
    -0.57
    ChildScrollView
    -0.57
     kaarangay
    -0.56
     ),
    -0.56
    POSITIVE LOGITS
    .
    0.75
    बाह
    0.52
    ;
    0.50
     separately
    0.49
     intenção
    0.43
     clínicos
    0.43
     őket
    0.43
     hoped
    0.42
     cientí
    0.42
     elér
    0.42
    Activations Density 0.003%

    No Known Activations