© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41151
    Prev
    Next
    INDEX
    Explanations

    overriding

    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
    SourceChecksum
    -0.95
    jspx
    -0.69
     overriding
    -0.68
     initComponents
    -0.63
    TagMode
    -0.59
    ophiles
    -0.59
     beaming
    -0.57
    OLVED
    -0.55
     Elders
    -0.55
    meanor
    -0.54
    POSITIVE LOGITS
    PickerController
    0.52
    ientôt
    0.51
     nemlig
    0.50
    RetentionPolicy
    0.49
    ésult
    0.49
    ifiz
    0.47
     PNC
    0.47
    od
    0.45
    impôt
    0.45
    цездатний
    0.45
    Activations Density 0.052%

    No Known Activations