© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 903
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     Try
    -0.49
    onuc
    -0.48
     DSC
    -0.47
     Inc
    -0.46
    ску
    -0.45
     dru
    -0.45
     pul
    -0.45
    }")]
    -0.44
    burgo
    -0.44
     ca
    -0.44
    POSITIVE LOGITS
     disponibilités
    0.66
    StoreMessageInfo
    0.63
    Lähteet
    0.63
     snippetHide
    0.62
     AspNetCore
    0.62
    ismet
    0.60
     jsPsych
    0.59
    writeFieldEnd
    0.58
     betweenstory
    0.56
    hatenablog
    0.54
    Activations Density 0.051%

    No Known Activations