© 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. 0-CLT-HP
    7. 93588
    Prev
    Next
    INDEX
    Explanations

    rented

    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
    __":
    -1.02
     myſelf
    -1.02
     AssemblyCulture
    -0.93
     himſelf
    -0.89
    DIPSETTING
    -0.88
     nahilalakip
    -0.86
    __':
    -0.86
     anſ
    -0.85
     fubject
    -0.85
    thâu
    -0.84
    POSITIVE LOGITS
    mybatisplus
    0.47
    und
    0.45
     
    0.44
     Al
    0.43
    um
    0.43
    1
    0.42
     G
    0.41
     al
    0.41
     as
    0.41
     O
    0.40
    Activations Density 0.135%

    No Known Activations