© 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. 0-CLT-HP
    4. 38260
    Prev
    Next
    INDEX
    Explanations

    first look/impressions

    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
    StoryboardSegue
    -0.77
    AutoresizingMask
    -0.74
     Theſe
    -0.73
     houſe
    -0.73
     Houſe
    -0.72
    DockStyle
    -0.69
     "..\..\..\
    -0.69
     himſelf
    -0.67
    evich
    -0.67
     ſever
    -0.66
    POSITIVE LOGITS
     rowspan
    0.48
    Slf
    0.46
    M
    0.45
     M
    0.45
    \}_{
    0.45
    行的
    0.44
    nables
    0.42
    deserved
    0.42
     Me
    0.41
     aguas
    0.41
    Activations Density 0.161%

    No Known Activations