© 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. 4-CLT-HP
    7. 632
    Prev
    Next
    INDEX
    Explanations

    the

    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
    PerformLayout
    -0.54
    ItemLayout
    -0.54
     agrí
    -0.53
    き
    -0.52
    ModelForm
    -0.51
    Etimología
    -0.50
    eradish
    -0.49
    IsPostBack
    -0.47
     klim
    -0.46
    明
    -0.46
    POSITIVE LOGITS
    GOTREF
    0.59
    ?}",
    0.59
    TagMode
    0.59
    исленность
    0.54
     createState
    0.53
    
    0.51
    DrawerToggle
    0.50
    ]--;
    0.48
     Perrin
    0.48
    saraba
    0.47
    Activations Density 0.008%

    No Known Activations