© 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. 93220
    Prev
    Next
    INDEX
    Explanations

    which

    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
     myſelf
    -0.93
    ^(@)
    -0.88
     itſelf
    -0.84
    NUMX
    -0.83
     faſt
    -0.81
     purpoſe
    -0.76
    SequentialGroup
    -0.76
     himſelf
    -0.74
     themſelves
    -0.72
     ―――――
    -0.69
    POSITIVE LOGITS
    InteropServices
    0.56
     inmediato
    0.51
    ;
    0.49
     and
    0.48
    ,
    0.46
    opsida
    0.44
    Datuak
    0.43
    <eos>
    0.43
    MigrationBuilder
    0.43
     WaitForSeconds
    0.42
    Activations Density 0.005%

    No Known Activations