© 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. 15526
    Prev
    Next
    INDEX
    Explanations

    ins

    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
     <<<<<<<<<<<<<<
    -0.58
    țul
    -0.49
    粱
    -0.46
    ь
    -0.43
    putstr
    -0.41
     địa
    -0.40
    j
    -0.40
    fhir
    -0.40
    供
    -0.40
    getDisplay
    -0.40
    POSITIVE LOGITS
    fjspx
    0.84
     CanadaChoose
    0.76
    pherals
    0.71
    Personensuche
    0.69
     CreateTagHelper
    0.66
     utafitiHapana
    0.66
     '\\;'
    0.65
    .":
    0.65
    tvguidetime
    0.63
    ]]:
    0.63
    Activations Density 0.020%

    No Known Activations