© 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. 20-CLT-HP
    7. 73462
    Prev
    Next
    INDEX
    Explanations

    Code and scripts

    np_max-act-logits · 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
    endphp
    -0.65
    WriteTagHelper
    -0.60
    awakeFromNib
    -0.59
     '\\;'
    -0.58
     trajets
    -0.57
    DockStyle
    -0.56
    RemoteException
    -0.55
    terraform
    -0.54
     تضيفلها
    -0.54
    PONSE
    -0.54
    POSITIVE LOGITS
     Gres
    0.51
    ukone
    0.48
    jgl
    0.43
     Gret
    0.42
    Rib
    0.39
    weiß
    0.39
     Bünd
    0.38
    Diwedd
    0.38
     Trout
    0.37
    HasAnnotation
    0.37
    Activations Density 0.001%

    No Known Activations