© 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. 94116
    Prev
    Next
    INDEX
    Explanations

    loss

    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
    webElementXpaths
    -0.70
    AddTagHelper
    -0.70
    InjectAttribute
    -0.69
    ValueStyle
    -0.68
     doInBackground
    -0.63
     '\\;'
    -0.60
     combatt
    -0.59
     PopupWindow
    -0.57
     onData
    -0.56
    SequentialGroup
    -0.53
    POSITIVE LOGITS
    ########.
    0.65
    ⓧ
    0.58
    WriteTagHelper
    0.57
     phenotypes
    0.52
    jiri
    0.52
     embryonic
    0.52
     pathogenesis
    0.52
     embry
    0.51
    #+#
    0.51
     setContent
    0.51
    Activations Density 0.509%

    No Known Activations