© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92683
    Prev
    Next
    INDEX
    Explanations

    references between different items

    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
     betreft
    -0.51
     parlé
    -0.51
     estekak
    -0.47
     "..\..\..\
    -0.46
     parlent
    -0.45
    Werdegang
    -0.45
    Particular
    -0.43
    ADVERTISEMENT
    -0.42
     territoriale
    -0.42
    PARTIC
    -0.41
    POSITIVE LOGITS
     year
    0.69
     week
    0.65
    الدراسه
    0.64
    NAMES
    0.60
     month
    0.57
     Monday
    0.57
    PositiveButton
    0.57
    GenerationType
    0.56
     day
    0.55
     morning
    0.55
    Activations Density 0.016%

    No Known Activations