© 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. 1-CLT-HP
    7. 9890
    Prev
    Next
    INDEX
    Explanations

    shortcut

    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
    AddTagHelper
    -0.78
    Хьажоргаш
    -0.64
    rungsseite
    -0.61
    abetes
    -0.60
    OwnProperty
    -0.60
     evangé
    -0.60
    StoryboardSegue
    -0.59
     myſelf
    -0.57
     faſt
    -0.57
     purpoſe
    -0.57
    POSITIVE LOGITS
     ge
    0.47
     presence
    0.46
    nein
    0.46
    NOK
    0.45
    ош
    0.45
     Ball
    0.44
    orgen
    0.44
     anim
    0.43
    έσ
    0.43
     motion
    0.43
    Activations Density 0.017%

    No Known Activations