© 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. 1-CLT-HP
    7. 13699
    Prev
    Next
    INDEX
    Explanations

    than

    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
     than
    -0.66
     and
    -0.64
     or
    -0.59
    than
    -0.58
    __((
    -0.52
     Than
    -0.51
    Than
    -0.50
     ?>>
    -0.48
     THAN
    -0.47
     kuin
    -0.47
    POSITIVE LOGITS
     beginnetje
    0.74
     مشين
    0.71
    AutoScaleMode
    0.67
    expandindo
    0.66
    OGND
    0.66
     AssemblyCompany
    0.65
     pinulongan
    0.64
    GIVEREF
    0.64
    WireFormatLite
    0.63
    ngdoc
    0.60
    Activations Density 0.007%

    No Known Activations