© 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. 72453
    Prev
    Next
    INDEX
    Explanations

    aspects, elements, factors

    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
    GEBURTSDATUM
    -0.73
     Meksiku
    -0.52
    HasColumnName
    -0.48
    ضير
    -0.47
    principalTable
    -0.46
     télécommande
    -0.45
    fjspx
    -0.44
     ComVisible
    -0.44
    IntoConstraints
    -0.44
    blå
    -0.43
    POSITIVE LOGITS
     aspect
    1.05
     example
    0.87
     element
    0.87
     reason
    0.85
     option
    0.84
     factor
    0.83
     approach
    0.82
     mechanism
    0.82
     thing
    0.81
     suggestion
    0.81
    Activations Density 0.000%

    No Known Activations