© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    is or s

    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
     ثم
    -0.43
    LayoutStyle
    -0.42
    zor
    -0.40
    makeConstraints
    -0.39
    use
    -0.39
    Them
    -0.38
     proble
    -0.38
    ই
    -0.38
    ystis
    -0.37
    unset
    -0.37
    POSITIVE LOGITS
    TagHelper
    0.89
     an
    0.75
     utafitiHapana
    0.69
    IndentedString
    0.69
     propOrder
    0.68
     intptr
    0.68
    ⓧ
    0.68
     SwitchCompat
    0.68
    ########.
    0.67
     AppCompatTheme
    0.66
    Activations Density 0.015%

    No Known Activations