© 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. 1-CLT-HP
    7. 10624
    Prev
    Next
    INDEX
    Explanations

    technical/academic text

    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
    mera
    -0.44
    graph
    -0.44
    ばら
    -0.44
    sing
    -0.44
    Decided
    -0.43
    genome
    -0.42
    pairs
    -0.42
    meras
    -0.42
     sp
    -0.41
    createClass
    -0.41
    POSITIVE LOGITS
     Administrativna
    0.72
     kasarigan
    0.66
     ModelRenderer
    0.66
     سكانية
    0.65
    EndContext
    0.64
    }$​
    0.62
    })*/
    0.62
     TextAppearance
    0.62
    ſelf
    0.61
     Оно
    0.60
    Activations Density 0.017%

    No Known Activations