© 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. 0-CLT-HP
    7. 43687
    Prev
    Next
    INDEX
    Explanations

    of

    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
     betweenstory
    -0.49
     comp
    -0.42
    ця
    -0.39
    tività
    -0.38
    Continue
    -0.38
     gre
    -0.38
    ram
    -0.38
    setLayout
    -0.37
    maple
    -0.36
     тя
    -0.36
    POSITIVE LOGITS
     Савезне
    0.94
    httphttps
    0.92
    ArgsConstructor
    0.86
    SourceChecksum
    0.85
    WireFormatLite
    0.79
    enumii
    0.77
    ]")]
    0.77
    DeleteBehavior
    0.77
    AnimationsModule
    0.76
    tagHelperRunner
    0.73
    Activations Density 0.088%

    No Known Activations