© 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. 97157
    Prev
    Next
    INDEX
    Explanations

    (

    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
    UVWXYZ
    -0.58
    <eos>
    -0.56
     ExecuteAsync
    -0.56
    NOPQRST
    -0.54
     Italijani
    -0.54
    quale
    -0.54
     Италијани
    -0.54
    ]}"
    -0.53
    Portail
    -0.52
    softc
    -0.52
    POSITIVE LOGITS
     ſhe
    0.58
     myſelf
    0.57
     anſ
    0.52
     purpoſe
    0.51
     themſelves
    0.51
     himſelf
    0.51
     Efq
    0.51
     beelden
    0.50
     Anſ
    0.50
    kuuta
    0.50
    Activations Density 0.006%

    No Known Activations