© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43244
    Prev
    Next
    INDEX
    Explanations

    Jer

    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
    findpost
    -0.61
    twimg
    -0.60
     Dal
    -0.59
     kasarigan
    -0.56
    BeginContext
    -0.54
    ModelSerializer
    -0.52
    AndroidJUnit
    -0.51
    teer
    -0.51
    ंदीखरीदारी
    -0.49
     menang
    -0.49
    POSITIVE LOGITS
    ing
    0.69
    thschild
    0.65
     RIPRODUZIONE
    0.65
    jublj
    0.54
     <<<<<<<<<<<<<<
    0.54
     trebui
    0.54
    +#+#
    0.54
     Halen
    0.54
    matchCondition
    0.53
     Aphrodite
    0.52
    Activations Density 0.039%

    No Known Activations