© 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. 4-CLT-HP
    7. 215
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     تضيفلها
    -0.89
    rungsseite
    -0.75
     متعلقه
    -0.65
    ſelves
    -0.65
    ppure
    -0.63
     Roskov
    -0.62
     Houſe
    -0.62
    ----</
    -0.61
     Anſ
    -0.61
    ]++;
    -0.59
    POSITIVE LOGITS
     res
    0.52
    <bos>
    0.47
     the
    0.46
     saites
    0.45
     Res
    0.45
     large
    0.45
    0
    0.44
     their
    0.43
     most
    0.42
     pens
    0.41
    Activations Density 0.027%

    No Known Activations