© 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. 96954
    Prev
    Next
    INDEX
    Explanations

    or

    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
    __(/*!
    -0.65
    OGND
    -0.60
     siglos
    -0.59
    verständlich
    -0.56
    "]}
    -0.55
     voorzien
    -0.54
     Ανακτήθηκε
    -0.54
     محفوظة
    -0.53
     سكانية
    -0.53
    sscanf
    -0.53
    POSITIVE LOGITS
     الحره
    0.66
    SourceChecksum
    0.55
     confuse
    0.52
     simulate
    0.52
     EconPapers
    0.50
    LayoutConstraint
    0.50
    kháu
    0.50
     prevent
    0.49
    Expedia
    0.48
     about
    0.46
    Activations Density 0.001%

    No Known Activations