© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92209
    Prev
    Next
    INDEX
    Explanations

    conversational beginnings

    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
    I
    -0.48
     tạm
    -0.46
     Wann
    -0.45
     Stimme
    -0.44
    h
    -0.43
     ettei
    -0.41
    Hvordan
    -0.41
    Well
    -0.41
    now
    -0.40
    въ
    -0.40
    POSITIVE LOGITS
    ंदीखरीदारी
    1.36
     CreateTagHelper
    0.95
    ReusableCell
    0.84
    StructEnd
    0.83
    Geplaatst
    0.83
    tagHelperRunner
    0.81
    IUrlHelper
    0.81
    Personensuche
    0.80
    DockStyle
    0.78
     برانيه
    0.77
    Activations Density 0.014%

    No Known Activations