© 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. 20-CLT-HP
    7. 77325
    Prev
    Next
    INDEX
    Explanations

    Code/Programming related texts

    np_max-act-logits · 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
    ]--;
    -0.66
    LabelTagHelper
    -0.65
    tvguidetime
    -0.61
     صوتيه
    -0.59
    esgue
    -0.57
    phobia
    -0.56
    ốp
    -0.54
     createStore
    -0.54
    })`
    -0.53
     الحره
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.59
     reflected
    0.57
     contact
    0.57
     reflection
    0.53
     Sed
    0.52
     ra
    0.52
    PerformLayout
    0.52
    PyExc
    0.47
     Ahl
    0.47
     ramp
    0.45
    Activations Density 0.000%

    No Known Activations