© 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. 5-CLT-HP
    7. 5936
    Prev
    Next
    INDEX
    Explanations

    us are

    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
    UserScript
    -0.86
    Autoritní
    -0.74
    __':
    -0.59
    Personendaten
    -0.59
     nakalista
    -0.57
    NameInMap
    -0.56
     kasarigan
    -0.56
    .*")]
    -0.55
    OGND
    -0.54
     onAnimation
    -0.54
    POSITIVE LOGITS
     détach
    0.53
     dépens
    0.52
     noastre
    0.51
     mérit
    0.50
    ceğini
    0.50
     soeur
    0.49
     tänker
    0.48
    GetAxis
    0.48
     déclar
    0.48
     restent
    0.48
    Activations Density 0.005%

    No Known Activations