© 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. 97018
    Prev
    Next
    INDEX
    Explanations

    aster

    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
     CreateTagHelper
    -0.83
     nakalista
    -0.82
    CPtr
    -0.66
    alini
    -0.65
    GenerationType
    -0.65
     متعلقه
    -0.65
     gynhyrchwyd
    -0.64
     Theſe
    -0.63
    RegistryLite
    -0.62
    IsMutable
    -0.62
    POSITIVE LOGITS
    mente
    0.54
    ty
    0.53
    ke
    0.50
    ms
    0.49
    wpi
    0.48
    ki
    0.48
    gu
    0.47
    WithIdentifier
    0.47
    men
    0.47
    ite
    0.47
    Activations Density 0.180%

    No Known Activations