© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91625
    Prev
    Next
    INDEX
    Explanations

    considering, processing

    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
    ंदीखरीदारी
    -0.60
    cinfo
    -0.52
     Almost
    -0.52
    almost
    -0.51
    hésite
    -0.50
     estimés
    -0.48
    Almost
    -0.48
     "..\..\
    -0.47
     almost
    -0.47
    thinkable
    -0.47
    POSITIVE LOGITS
    GIVEREF
    0.71
    DockStyle
    0.71
    CreateMap
    0.59
    setVerticalGroup
    0.59
    CodedInputStream
    0.58
    ursue
    0.57
    ądź
    0.53
    ább
    0.53
    MethodImpl
    0.52
    URLException
    0.52
    Activations Density 0.036%

    No Known Activations