© 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. 93924
    Prev
    Next
    INDEX
    Explanations

    take

    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
     oblige
    -0.60
    +#+#
    -0.59
    addComponent
    -0.56
     themselves
    -0.56
    脚注の使い方
    -0.55
    rimir
    -0.53
    LabelTagHelper
    -0.52
     nahilalakip
    -0.52
    ValueMap
    -0.51
     ddelweddau
    -0.50
    POSITIVE LOGITS
    hoeddwyd
    0.58
    inergic
    0.53
    showConfirm
    0.53
    derabad
    0.52
    ❹
    0.51
     réserve
    0.50
     actif
    0.50
     viewDidLoad
    0.50
     singoli
    0.50
    anstalt
    0.49
    Activations Density 0.011%

    No Known Activations