© 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. 5-CLT-HP
    7. 91972
    Prev
    Next
    INDEX
    Explanations

    travel routes

    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
    #+#
    -0.57
    ValueStyle
    -0.55
    unhofer
    -0.53
    enumii
    -0.53
    orianCalendar
    -0.47
    vinte
    -0.47
     ProtoMessage
    -0.47
    blestone
    -0.46
    TestingModule
    -0.46
    AddTagHelper
    -0.46
    POSITIVE LOGITS
     connecting
    0.65
     linking
    0.59
     lies
    0.53
     giveaway
    0.52
    Connecting
    0.52
     Connecting
    0.52
     permitting
    0.51
     lying
    0.51
    ğraf
    0.50
    writeField
    0.49
    Activations Density 0.002%

    No Known Activations