© 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. 90914
    Prev
    Next
    INDEX
    Explanations

    Dh

    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
     uſe
    -0.85
     Chriftian
    -0.85
     purpoſe
    -0.84
     ſche
    -0.82
     ſtate
    -0.81
     Majefty
    -0.76
     pleaſure
    -0.76
     Reſ
    -0.74
     itſelf
    -0.74
     houſe
    -0.73
    POSITIVE LOGITS
    twimg
    0.59
    StackNavigator
    0.57
    Clue
    0.56
    aspectj
    0.54
    MessageOf
    0.53
    олові
    0.53
     SqlCommand
    0.52
    endregion
    0.51
    uduk
    0.51
    writeFieldEnd
    0.51
    Activations Density 1.117%

    No Known Activations