© 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. 5-CLT-HP
    7. 3993
    Prev
    Next
    INDEX
    Explanations

    federal

    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
    -0.63
     nahilalakip
    -0.57
    المكان
    -0.57
     or
    -0.52
    Jeografia
    -0.51
     Meksiku
    -0.51
    gnings
    -0.50
    bewerken
    -0.50
    涯
    -0.49
    nde
    -0.49
    POSITIVE LOGITS
    ValueGeneration
    0.67
    RectangleBorder
    0.61
    Бахар
    0.60
     ℃
    0.50
    rawDesc
    0.48
     DPR
    0.48
    HostException
    0.47
    hopped
    0.47
    __":
    0.47
    /*
    0.46
    Activations Density 0.000%

    No Known Activations