© 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. 93070
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    cul
    -0.58
    rungsseite
    -0.57
    uchar
    -0.54
    serve
    -0.54
    complexContent
    -0.53
    coop
    -0.52
    tain
    -0.52
    Harp
    -0.52
    ikou
    -0.52
    octubre
    -0.51
    POSITIVE LOGITS
    rawDesc
    0.51
    ποτε
    0.43
     թվական
    0.42
    Infl
    0.40
     Pent
    0.40
    strijden
    0.40
    standers
    0.40
    rode
    0.39
    UrlResolution
    0.39
    "])
    0.39
    Activations Density 0.000%

    No Known Activations