© 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. 0-CLT-HP
    7. 90593
    Prev
    Next
    INDEX
    Explanations

    rooted

    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
     Himo
    -0.65
    StoryboardSegue
    -0.62
    petit
    -0.57
     MST
    -0.57
     meridian
    -0.57
    XmlAccessorType
    -0.55
    buses
    -0.54
     nakalista
    -0.54
    Datuak
    -0.54
    BufferException
    -0.53
    POSITIVE LOGITS
    طلاق
    0.50
    s
    0.49
    enumi
    0.49
    jsii
    0.48
    izo
    0.47
    ("~/
    0.46
    ngrx
    0.46
    pstmt
    0.45
    nalités
    0.44
    WriteTagHelper
    0.43
    Activations Density 0.614%

    No Known Activations