© 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. 1-CLT-HP
    7. 9109
    Prev
    Next
    INDEX
    Explanations

    estino

    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
    estin
    -1.59
     تضيفلها
    -1.09
     виправивши
    -0.89
    Geplaatst
    -0.88
     SwitchCompat
    -0.84
    évaluateur
    -0.83
     referenties
    -0.79
    findpost
    -0.78
    paravant
    -0.78
     الرياضيه
    -0.77
    POSITIVE LOGITS
    bootstrapcdn
    0.54
    gha
    0.44
    creva
    0.41
    arbonato
    0.41
    Sib
    0.41
    got
    0.40
     una
    0.40
    datab
    0.40
    asına
    0.40
    心
    0.40
    Activations Density 0.191%

    No Known Activations