© 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. 1-CLT-HP
    4. 15512
    Prev
    Next
    INDEX
    Explanations

    spent

    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
    ſelf
    -0.71
     ainfi
    -0.68
     purpoſe
    -0.66
     Anſ
    -0.64
     beſt
    -0.63
     leaſt
    -0.63
     Challenges
    -0.63
     Reſ
    -0.62
    νό
    -0.60
     iſt
    -0.60
    POSITIVE LOGITS
    XmlAccessType
    0.74
    <bos>
    0.52
    CppMethod
    0.50
    rawDesc
    0.49
    ExecuteReader
    0.49
    #+#
    0.49
    ddha
    0.47
    sidemargin
    0.47
    tvguidetime
    0.47
    帖最后由
    0.47
    Activations Density 0.036%

    No Known Activations