© 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. 4-CLT-HP
    7. 1575
    Prev
    Next
    INDEX
    Explanations

    belt

    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
    __':
    -0.58
    ?}",
    -0.55
    MergeFrom
    -0.55
    chemise
    -0.51
    ollectionView
    -0.50
     cracks
    -0.50
    ItemGroup
    -0.49
    __":
    -0.49
    movq
    -0.49
    akka
    -0.49
    POSITIVE LOGITS
     Linder
    0.53
    éditeur
    0.48
     يتيمه
    0.48
    IUrlHelper
    0.46
    Victorian
    0.46
    woners
    0.44
    batore
    0.44
    бище
    0.43
    Abstra
    0.42
     abiertas
    0.42
    Activations Density 0.009%

    No Known Activations