© 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. 4-CLT-HP
    7. 3095
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    出版年
    -0.57
    EDEFAULT
    -0.46
     such
    -0.43
     states
    -0.42
     Namens
    -0.42
    ,
    -0.42
    ECONDS
    -0.42
     Begründung
    -0.41
     (
    -0.40
     ,
    -0.40
    POSITIVE LOGITS
    fjspx
    0.82
     المعيارى
    0.71
    principalColumn
    0.71
    IUrlHelper
    0.71
     FetchType
    0.63
    IntoConstraints
    0.63
    complexContent
    0.60
     Dormit
    0.59
     glare
    0.58
     ErrIntOverflow
    0.58
    Activations Density 0.002%

    No Known Activations