© 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. 5-CLT-HP
    7. 97591
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ,
    -0.65
    /
    -0.58
    StructEnd
    -0.49
    İstinadlar
    -0.42
     même
    -0.40
     More
    -0.40
    Even
    -0.40
     denen
    -0.40
     možnosti
    -0.40
     addirittura
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.80
    AndEndTag
    0.68
    ſelf
    0.67
     CreateTagHelper
    0.66
    Autoritní
    0.64
    ])).
    0.62
    ſelves
    0.61
    lorette
    0.61
    GrantedAuthority
    0.61
     myſelf
    0.61
    Activations Density 0.009%

    No Known Activations