© 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. 1-CLT-HP
    7. 10373
    Prev
    Next
    INDEX
    Explanations

    DM

    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
     DM
    -0.60
    dm
    -0.54
     dm
    -0.52
     ചെയ
    -0.51
    parsedMessage
    -0.50
    DM
    -0.50
    دانشنامهٔ
    -0.49
     enjo
    -0.43
     gibts
    -0.41
    m
    -0.41
    POSITIVE LOGITS
    InteropServices
    0.64
    ]")]
    0.63
    invokeLater
    0.61
     IActionResult
    0.60
    endphp
    0.60
    hena
    0.59
    SequentialGroup
    0.58
    GrantedAuthority
    0.57
    Tazama
    0.56
    Kaynakça
    0.54
    Activations Density 0.017%

    No Known Activations