© 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. 5309
    Prev
    Next
    INDEX
    Explanations

    soldering

    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
    KIN
    -0.60
    kin
    -0.57
     hjelp
    -0.54
     hjælp
    -0.52
     Circuit
    -0.49
    Circuit
    -0.48
    InlineData
    -0.47
    ちな
    -0.47
     refroidissement
    -0.45
    Help
    -0.45
    POSITIVE LOGITS
     Chwiliwch
    0.82
     ProtoMessage
    0.82
    AndEndTag
    0.70
     CreateTagHelper
    0.69
    enderror
    0.66
    Chham
    0.61
    ScopeManager
    0.55
    avajillas
    0.52
    sidemargin
    0.52
     DL
    0.52
    Activations Density 0.006%

    No Known Activations