© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94372
    Prev
    Next
    INDEX
    Explanations

    path

    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
     path
    -2.14
     Path
    -1.93
    Path
    -1.67
    path
    -1.58
     PATH
    -1.24
     pathway
    -1.22
    PATH
    -1.20
     paths
    -1.16
     track
    -1.09
     Pathway
    -1.07
    POSITIVE LOGITS
     Efq
    0.92
     ―――――
    0.84
     Monfieur
    0.84
    Personensuche
    0.83
     raiſ
    0.82
     myſelf
    0.81
    Datuak
    0.81
     ་་
    0.80
     Houſe
    0.79
     pinulongan
    0.77
    Activations Density 0.167%

    No Known Activations