© 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. 97525
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    EndInit
    -0.63
     hunter
    -0.58
     hunters
    -0.55
    raco
    -0.54
     authentic
    -0.54
     arşivlendi
    -0.54
    Chham
    -0.52
     SearchView
    -0.52
     haunted
    -0.52
     truncated
    -0.52
    POSITIVE LOGITS
    Tikang
    0.57
    SPATH
    0.52
     preocu
    0.51
     '\\;'
    0.45
    AccessorTable
    0.45
    EDEFAULT
    0.44
    UserScript
    0.43
     grij
    0.42
    jsii
    0.42
    xodo
    0.42
    Activations Density 0.001%

    No Known Activations