© 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. 0-CLT-HP
    7. 41335
    Prev
    Next
    INDEX
    Explanations

    past

    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
     ligiloj
    -0.74
    hur
    -0.64
    帖最后由
    -0.58
     HUR
    -0.57
    PerformLayout
    -0.56
     winners
    -0.54
    锈钢
    -0.54
     Wiktionnaire
    -0.53
     Chwiliwch
    -0.52
    PyTuple
    -0.52
    POSITIVE LOGITS
     ujednoznacz
    0.63
    ījum
    0.54
    ysty
    0.52
    räck
    0.52
    ADATA
    0.51
    ={({
    0.50
    ]")]
    0.49
    stag
    0.47
     UnityEditor
    0.46
     JOUR
    0.46
    Activations Density 1.538%

    No Known Activations