© 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. 0-CLT-HP
    7. 94018
    Prev
    Next
    INDEX
    Explanations

    Undesirable states

    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
     bells
    -0.80
    rr
    -0.71
     Bells
    -0.64
    rrr
    -0.59
    rrrr
    -0.52
    rrrrr
    -0.48
     Sudbury
    -0.47
    τερα
    -0.46
    aryen
    -0.45
    ialog
    -0.44
    POSITIVE LOGITS
     getRule
    0.71
    ChildScrollView
    0.69
    ImageContext
    0.66
    ]--;
    0.65
    eseorang
    0.61
     Вікі
    0.60
    Amicalement
    0.60
    writerow
    0.60
    sizeCache
    0.59
     مرئيه
    0.59
    Activations Density 0.099%

    No Known Activations