© 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. 92654
    Prev
    Next
    INDEX
    Explanations

    example

    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
    
    -0.78
    pædia
    -0.66
    ItemBackground
    -0.64
     snippetHide
    -0.61
    ']}
    -0.59
    tinyos
    -0.59
     AssemblyCulture
    -0.59
    AnchorStyles
    -0.58
     utafitiHapana
    -0.57
    DockStyle
    -0.57
    POSITIVE LOGITS
    SPATH
    0.51
     entered
    0.47
     format
    0.46
     noastre
    0.46
     desglose
    0.45
     entró
    0.43
     indisponible
    0.43
    FileDialog
    0.43
     entries
    0.41
    ải
    0.40
    Activations Density 0.001%

    No Known Activations