© 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. 1-CLT-HP
    7. 799
    Prev
    Next
    INDEX
    Explanations

    Issues, problems

    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
    SBATCH
    -0.63
    Kaynakça
    -0.63
    脚注の使い方
    -0.61
    \|_{\
    -0.61
     fhew
    -0.60
    StateToProps
    -0.60
    ToProps
    -0.59
     whoſe
    -0.58
     Metacritic
    -0.58
    ArgsConstructor
    -0.58
    POSITIVE LOGITS
    CppMethod
    0.63
    oredCriteria
    0.61
    principalTable
    0.57
    SequentialGroup
    0.56
    ProcessEvent
    0.52
    memoized
    0.48
    nodoc
    0.46
     lay
    0.44
     nahilalakip
    0.43
    LOP
    0.39
    Activations Density 0.008%

    No Known Activations