© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97680
    Prev
    Next
    INDEX
    Explanations

    to

    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
    InitVars
    -0.98
     GenerationType
    -0.87
     يتيمه
    -0.86
     själva
    -0.85
    featureID
    -0.85
    期刊论文
    -0.84
     betweenstory
    -0.83
    AndEndTag
    -0.83
    LookAnd
    -0.82
     contextLoads
    -0.82
    POSITIVE LOGITS
     ten
    0.76
     eight
    0.67
     six
    0.62
     
    0.60
     one
    0.60
     nine
    0.60
     five
    0.59
     f
    0.59
     seven
    0.58
     se
    0.54
    Activations Density 0.001%

    No Known Activations