© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4174
    Prev
    Next
    INDEX
    Explanations

    gas or expulsion

    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
    OGND
    -0.59
     beginnetje
    -0.58
     externi
    -0.52
    قایناق‌لار
    -0.50
     мәкал
    -0.48
     Kore
    -0.45
    ätt
    -0.45
    imer
    -0.44
    <bos>
    -0.44
     VIAF
    -0.44
    POSITIVE LOGITS
     from
    0.64
    mbals
    0.61
     Ressources
    0.57
    StringCopy
    0.55
     referrerpolicy
    0.54
    Portail
    0.54
    Strongly
    0.54
    eapple
    0.53
     désolés
    0.53
    zzles
    0.52
    Activations Density 0.012%

    No Known Activations