© 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. 4-CLT-HP
    7. 1434
    Prev
    Next
    INDEX
    Explanations

    Mining

    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
     Wikimedijinoj
    -0.69
     utafitiHapana
    -0.66
    interopRequire
    -0.66
    webElementXpaths
    -0.63
    #+#
    -0.62
    adaptiveStyles
    -0.62
    ädie
    -0.60
    脚注の使い方
    -0.60
     continuant
    -0.59
    findpost
    -0.58
    POSITIVE LOGITS
    <bos>
    0.92
     mines
    0.77
     mining
    0.71
     mine
    0.66
     miners
    0.65
    Mines
    0.63
    mines
    0.63
    Mine
    0.63
     Mines
    0.61
     Mine
    0.61
    Activations Density 0.026%

    No Known Activations