© 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. 93916
    Prev
    Next
    INDEX
    Explanations

    government and organizations

    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
    しも
    -0.57
     mineral
    -0.49
    CGRectMake
    -0.44
    Uninitialized
    -0.44
    阔
    -0.43
     modified
    -0.43
     doGet
    -0.42
    forRoot
    -0.42
    idah
    -0.41
    nov
    -0.41
    POSITIVE LOGITS
    Tikang
    0.81
    bootstrapcdn
    0.80
    StructEnd
    0.67
     المعيارى
    0.64
    onAttach
    0.62
    Personensuche
    0.58
    tanleria
    0.58
     autorytatywna
    0.58
    addCriterion
    0.57
    ósito
    0.57
    Activations Density 0.063%

    No Known Activations