© 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. 96799
    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
    flashdata
    -0.56
    MockBean
    -0.49
    AutoresizingMask
    -0.48
    хьтан
    -0.47
    mặt
    -0.47
     baseURL
    -0.45
    formKey
    -0.45
    SourceChecksum
    -0.44
     BioLib
    -0.43
     Invention
    -0.42
    POSITIVE LOGITS
    PerformLayout
    0.74
    Бахар
    0.61
    BeginContext
    0.58
    Carriera
    0.56
     olev
    0.52
     babi
    0.50
    djangoproject
    0.50
    ẹ
    0.50
     Princess
    0.48
    textrm
    0.48
    Activations Density 0.002%

    No Known Activations